Daily Papers

The trajectory of AI development suggests that we will increasingly rely on agent-based systems composed of independently developed agents with different information, privileges, and tools. The success of these systems will critically depend on effective collaboration among these heterogeneous agents, even under partial observability. Despite intense interest, few empirical studies have evaluated such agent-agent collaboration at scale. We propose a collaborative maze-solving benchmark that (i) isolates collaborative capabilities, (ii) modulates problem complexity, (iii) enables scalable automated grading, and (iv) imposes no output-format constraints, preserving ecological plausibility. Using this framework, we evaluate 32 leading open- and closed-source models in solo, homogeneous, and heterogeneous pairings. Our results reveal a "collaboration gap": models that perform well solo often degrade substantially when required to collaborate. Collaboration can break down dramatically; for instance, small distilled models that solve mazes well alone may fail almost completely in certain pairings. We find that starting with the stronger agent often improves outcomes, motivating a "relay inference" approach where the stronger agent leads before handing off to the weaker one, closing much of the gap. Our findings argue for (1) collaboration-aware evaluation, (2) training strategies developed to enhance collaborative capabilities, and (3) interaction design that reliably elicits agents' latent skills, guidance that applies to AI-AI and human-AI collaboration.

We study how different Chain-of-Thought (CoT) designs affect the acquisition of the generalizable visual reasoning ability in vision-language models (VLMs). While CoT data, especially long or visual CoT such as "think with image", has been widely used to supervise intermediate reasoning, it remains unclear why specific CoT designs help and which ones truly support generalizable reasoning. To systematically evaluate this, we focus on a controlled maze-solving benchmark where reasoning rules are fully visual, difficulty can be tuned by grid size, and all the intermediate steps can be automatically generated. Using Qwen2.5-VL-7B under a standard SFT-then-RL pipeline, we compare three representative CoT formats: Language CoT, Grounding CoT (with spatial coordinate trajectories), and Visual CoT (with image manipulations). Our experiments reveal that visual and longer CoT mainly accelerate convergence but do not lift the final performance ceiling; concise CoT containing only essential grounding steps outperforms longer traces; and, strikingly, CoT retaining only the minimal grounding results generalizes best across different maze sizes. We further validate these insights on other vision-centric tasks. These findings highlight a "short is long" effect and provide practical guidance for constructing more generalizable SFT datasets for visual reasoning.

Video Models have achieved remarkable success in high-fidelity video generation with coherent motion dynamics. Analogous to the development from text generation to text-based reasoning in language modeling, the development of video models motivates us to ask: Can video models reason via video generation? Compared with the discrete text corpus, video grounds reasoning in explicit spatial layouts and temporal continuity, which serves as an ideal substrate for spatial reasoning. In this work, we explore the reasoning via video paradigm and introduce VR-Bench -- a comprehensive benchmark designed to systematically evaluate video models' reasoning capabilities. Grounded in maze-solving tasks that inherently require spatial planning and multi-step reasoning, VR-Bench contains 7,920 procedurally generated videos across five maze types and diverse visual styles. Our empirical analysis demonstrates that SFT can efficiently elicit the reasoning ability of video model. Video models exhibit stronger spatial perception during reasoning, outperforming leading VLMs and generalizing well across diverse scenarios, tasks, and levels of complexity. We further discover a test-time scaling effect, where diverse sampling during inference improves reasoning reliability by 10--20%. These findings highlight the unique potential and scalability of reasoning via video for spatial reasoning tasks.

With the explosive influence caused by the success of large language models (LLM) like ChatGPT and GPT-4, there has been an extensive amount of recent work showing that foundation models can be used to solve a large variety of tasks. However, there is very limited work that shares insights on multi-agent planning. Multi-agent planning is different from other domains by combining the difficulty of multi-agent coordination and planning, and making it hard to leverage external tools to facilitate the reasoning needed. In this paper, we focus on the problem of multi-agent path finding (MAPF), which is also known as multi-robot route planning, and study the performance of solving MAPF with LLMs. We first show the motivating success on an empty room map without obstacles, then the failure to plan on the harder room map and maze map of the standard MAPF benchmark. We present our position on why directly solving MAPF with LLMs has not been successful yet, and we use various experiments to support our hypothesis. Based on our results, we discussed how researchers with different backgrounds could help with this problem from different perspectives.

Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent benchmarks effectively assess skills like tool use or performance on structured tasks, they often do not fully capture an agent's ability to operate autonomously in exploratory environments that demand sustained, self-directed reasoning over a long and growing context. To spur the development of agents capable of more robust intrinsic reasoning over long horizons, we introduce TextQuests, a benchmark based on the Infocom suite of interactive fiction games. These text-based adventures, which can take human players over 30 hours and require hundreds of precise actions to solve, serve as an effective proxy for evaluating AI agents on focused, stateful tasks. The benchmark is specifically designed to assess an LLM agent's capacity for self-contained problem-solving by precluding the use of external tools, thereby focusing on intrinsic long-context reasoning capabilities in an exploratory environment characterized by the need for trial-and-error learning and sustained problem-solving within a single interactive session. We release TextQuests at https://textquests.ai.

Most existing spatial reasoning benchmarks focus on static or globally observable environments, failing to capture the challenges of long-horizon reasoning and memory utilization under partial observability and dynamic changes. We introduce two dynamic spatial benchmarks, locally observable maze navigation and match-2 elimination that systematically evaluate models' abilities in spatial understanding and adaptive planning when local perception, environment feedback, and global objectives are tightly coupled. Each action triggers structural changes in the environment, requiring continuous update of cognition and strategy. We further propose a subjective experience-based memory mechanism for cross-task experience transfer and validation. Experiments show that our benchmarks reveal key limitations of mainstream models in dynamic spatial reasoning and long-term memory, providing a comprehensive platform for future methodological advances. Our code and data are available at https://anonymous.4open.science/r/EvoEmpirBench-143C/.

Existing reasoning benchmarks for large language models (LLMs) frequently fail to capture authentic creativity, often rewarding memorization of previously observed patterns. We address this shortcoming with Sudoku-Bench, a curated benchmark of challenging and unconventional Sudoku variants specifically selected to evaluate creative, multi-step logical reasoning. Sudoku variants form an unusually effective domain for reasoning research: each puzzle introduces unique or subtly interacting constraints, making memorization infeasible and requiring solvers to identify novel logical breakthroughs (``break-ins''). Despite their diversity, Sudoku variants maintain a common and compact structure, enabling clear and consistent evaluation. Sudoku-Bench includes a carefully chosen puzzle set, a standardized text-based puzzle representation, and flexible tools compatible with thousands of publicly available puzzles -- making it easy to extend into a general research environment. Baseline experiments show that state-of-the-art LLMs solve fewer than 15\% of puzzles unaided, highlighting significant opportunities to advance long-horizon, strategic reasoning capabilities.

Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities; however, they still struggle to perform well in complex, dynamic environments. Real-world tasks require handling intricate interactions, advanced spatial reasoning, long-term planning, and continuous exploration of new strategies-areas in which we lack effective methodologies for comprehensively evaluating these capabilities. To address this gap, we introduce BALROG, a novel benchmark designed to assess the agentic capabilities of LLMs and VLMs through a diverse set of challenging games. Our benchmark incorporates a range of existing reinforcement learning environments with varying levels of difficulty, including tasks that are solvable by non-expert humans in seconds to extremely challenging ones that may take years to master (e.g., the NetHack Learning Environment). We devise fine-grained metrics to measure performance and conduct an extensive evaluation of several popular open-source and closed-source LLMs and VLMs. Our findings indicate that while current models achieve partial success in the easier games, they struggle significantly with more challenging tasks. Notably, we observe severe deficiencies in vision-based decision-making, as models perform worse when visual representations of the environments are provided. We release BALROG as an open and user-friendly benchmark to facilitate future research and development in the agentic community.

Existing benchmarks for frontier models often test specialized, ``PhD-level'' knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark based on the NPR Sunday Puzzle Challenge that requires only general knowledge. Our benchmark is challenging for both humans and models, however correct solutions are easy to verify, and models' mistakes are easy to spot. Our work reveals capability gaps that are not evident in existing benchmarks: OpenAI o1 significantly outperforms other reasoning models that are on par on benchmarks that test specialized knowledge. Furthermore, our analysis of reasoning outputs uncovers new kinds of failures. DeepSeek R1, for instance, often concedes with ``I give up'' before providing an answer that it knows is wrong. R1 can also be remarkably ``uncertain'' in its output and in rare cases, it does not ``finish thinking,'' which suggests the need for an inference-time technique to ``wrap up'' before the context window limit is reached. We also quantify the effectiveness of reasoning longer with R1 and Gemini Thinking to identify the point beyond which more reasoning is unlikely to improve accuracy on our benchmark.

Benchmarks play a crucial role in the development and analysis of reinforcement learning (RL) algorithms. We identify that existing benchmarks used for research into open-ended learning fall into one of two categories. Either they are too slow for meaningful research to be performed without enormous computational resources, like Crafter, NetHack and Minecraft, or they are not complex enough to pose a significant challenge, like Minigrid and Procgen. To remedy this, we first present Craftax-Classic: a ground-up rewrite of Crafter in JAX that runs up to 250x faster than the Python-native original. A run of PPO using 1 billion environment interactions finishes in under an hour using only a single GPU and averages 90% of the optimal reward. To provide a more compelling challenge we present the main Craftax benchmark, a significant extension of the Crafter mechanics with elements inspired from NetHack. Solving Craftax requires deep exploration, long term planning and memory, as well as continual adaptation to novel situations as more of the world is discovered. We show that existing methods including global and episodic exploration, as well as unsupervised environment design fail to make material progress on the benchmark. We believe that Craftax can for the first time allow researchers to experiment in a complex, open-ended environment with limited computational resources.

Large Language Models have demonstrated strong performance on many established reasoning benchmarks. However, these benchmarks primarily evaluate structured skills like quantitative problem-solving, leaving a gap in assessing flexible, multifaceted reasoning abilities that are central to human intelligence. These abilities require integrating logical deduction with spatial awareness and constraint satisfaction, which current evaluations do not measure well. To address this, we introduce RiddleBench, a benchmark of 1,737 challenging puzzles in English designed to probe these core reasoning capabilities. Evaluation of state-of-the-art models on RiddleBench shows fundamental weaknesses. Even top proprietary models like Gemini 2.5 Pro, o3, and Claude 4 Sonnet achieve accuracy just above 60% (60.30%, 63.37%, and 63.16%). Analysis further reveals deep failures, including hallucination cascades (accepting flawed reasoning from other models) and poor self-correction due to a strong self-confirmation bias. Their reasoning is also fragile, with performance degrading significantly when constraints are reordered or irrelevant information is introduced. RiddleBench functions as a diagnostic tool for these issues and as a resource for guiding the development of more robust and reliable language models.

As a seemingly self-explanatory task, problem-solving has been a significant component of science and engineering. However, a general yet concrete formulation of problem-solving itself is missing. With the recent development of AI-based problem-solving agents, the demand for process-level verifiability is rapidly increasing yet underexplored. To fill these gaps, we present a principled formulation of problem-solving as a deterministic Markov decision process; a novel framework, FPS (Formal Problem-Solving), which utilizes existing FTP (formal theorem proving) environments to perform process-verified problem-solving; and D-FPS (Deductive FPS), decoupling solving and answer verification for better human-alignment. The expressiveness, soundness and completeness of the frameworks are proven. We construct three benchmarks on problem-solving: FormalMath500, a formalization of a subset of the MATH500 benchmark; MiniF2F-Solving and PutnamBench-Solving, adaptations of FTP benchmarks MiniF2F and PutnamBench. For faithful, interpretable, and human-aligned evaluation, we propose RPE (Restricted Propositional Equivalence), a symbolic approach to determine the correctness of answers by formal verification. We evaluate four prevalent FTP models and two prompting methods as baselines, solving at most 23.77% of FormalMath500, 27.47% of MiniF2F-Solving, and 0.31% of PutnamBench-Solving.

Visual-Interleaved Chain-of-Thought (VI-CoT) enables MLLMs to continually update their understanding and decisions based on step-wise intermediate visual states (IVS), much like a human would, which demonstrates impressive success in various tasks, thereby leading to emerged advancements in related benchmarks. Despite promising progress, current benchmarks provide models with relatively fixed IVS, rather than free-style IVS, whch might forcibly distort the original thinking trajectories, failing to evaluate their intrinsic reasoning capabilities. More importantly, existing benchmarks neglect to systematically explore the impact factors that IVS would impart to untamed reasoning performance. To tackle above gaps, we introduce a specialized benchmark termed ViC-Bench, consisting of four representive tasks: maze navigation, jigsaw puzzle, embodied long-horizon planning, and complex counting, where each task has dedicated free-style IVS generation pipeline supporting function calls. To systematically examine VI-CoT capability, we propose a thorough evaluation suite incorporating a progressive three-stage strategy with targeted new metrics. Besides, we establish Incremental Prompting Information Injection (IPII) strategy to ablatively explore the prompting factors for VI-CoT. We extensively conduct evaluations for 18 advanced MLLMs, revealing key insights into their VI-CoT capability. Our proposed benchmark is publicly open at Huggingface.

Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces methodological rigor, with many evaluations relying on benchmarking practices that lack transparency, robustness, or statistical grounding. In this work, we conduct a comprehensive empirical study and find that current mathematical reasoning benchmarks are highly sensitive to subtle implementation choices - including decoding parameters, random seeds, prompt formatting, and even hardware and software-framework configurations. Performance gains reported in recent studies frequently hinge on unclear comparisons or unreported sources of variance. To address these issues, we propose a standardized evaluation framework with clearly defined best practices and reporting standards. Using this framework, we reassess recent methods and find that reinforcement learning (RL) approaches yield only modest improvements - far below prior claims - and are prone to overfitting, especially on small-scale benchmarks like AIME24. In contrast, supervised finetuning (SFT) methods show consistently stronger generalization. To foster reproducibility, we release all code, prompts, and model outputs, for reasoning benchmarks, establishing more rigorous foundations for future work.

Planning is central to agents and agentic AI. The ability to plan, e.g., creating travel itineraries within a budget, holds immense potential in both scientific and commercial contexts. Moreover, optimal plans tend to require fewer resources compared to ad-hoc methods. To date, a comprehensive understanding of existing planning benchmarks appears to be lacking. Without it, comparing planning algorithms' performance across domains or selecting suitable algorithms for new scenarios remains challenging. In this paper, we examine a range of planning benchmarks to identify commonly used testbeds for algorithm development and highlight potential gaps. These benchmarks are categorized into embodied environments, web navigation, scheduling, games and puzzles, and everyday task automation. Our study recommends the most appropriate benchmarks for various algorithms and offers insights to guide future benchmark development.

Large Vision-Language Models (LVLMs) struggle with puzzles, which require precise perception, rule comprehension, and logical reasoning. Assessing and enhancing their performance in this domain is crucial, as it reflects their ability to engage in structured reasoning - an essential skill for real-world problem-solving. However, existing benchmarks primarily evaluate pre-trained models without additional training or fine-tuning, often lack a dedicated focus on reasoning, and fail to establish a systematic evaluation framework. To address these limitations, we introduce VGRP-Bench, a Visual Grid Reasoning Puzzle Benchmark featuring 20 diverse puzzles. VGRP-Bench spans multiple difficulty levels, and includes extensive experiments not only on existing chat LVLMs (e.g., GPT-4o), but also on reasoning LVLMs (e.g., Gemini-Thinking). Our results reveal that even the state-of-the-art LVLMs struggle with these puzzles, highlighting fundamental limitations in their puzzle-solving capabilities. Most importantly, through systematic experiments, we identify and analyze key factors influencing LVLMs' puzzle-solving performance, including the number of clues, grid size, and rule complexity. Furthermore, we explore two Supervised Fine-Tuning (SFT) strategies that can be used in post-training: SFT on solutions (S-SFT) and SFT on synthetic reasoning processes (R-SFT). While both methods significantly improve performance on trained puzzles, they exhibit limited generalization to unseen ones. We will release VGRP-Bench to facilitate further research on LVLMs for complex, real-world problem-solving. Project page: https://yufan-ren.com/subpage/VGRP-Bench/.

We introduce FloorplanQA, a diagnostic benchmark for evaluating spatial reasoning in large-language models (LLMs). FloorplanQA is grounded in structured representations of indoor scenes, such as (e.g., kitchens, living rooms, bedrooms, bathrooms, and others), encoded symbolically in JSON or XML layouts. The benchmark covers core spatial tasks, including distance measurement, visibility, path finding, and object placement within constrained spaces. Our results across a variety of frontier open-source and commercial LLMs reveal that while models may succeed in shallow queries, they often fail to respect physical constraints, preserve spatial coherence, though they remain mostly robust to small spatial perturbations. FloorplanQA uncovers a blind spot in today's LLMs: inconsistent reasoning about indoor layouts. We hope this benchmark inspires new work on language models that can accurately infer and manipulate spatial and geometric properties in practical settings.

While the field of Quality-Diversity (QD) has grown into a distinct branch of stochastic optimization, a few problems, in particular locomotion and navigation tasks, have become de facto standards. Are such benchmarks sufficient? Are they representative of the key challenges faced by QD algorithms? Do they provide the ability to focus on one particular challenge by properly disentangling it from others? Do they have much predictive power in terms of scalability and generalization? Existing benchmarks are not standardized, and there is currently no MNIST equivalent for QD. Inspired by recent works on Reinforcement Learning benchmarks, we argue that the identification of challenges faced by QD methods and the development of targeted, challenging, scalable but affordable benchmarks is an important step. As an initial effort, we identify three problems that are challenging in sparse reward settings, and propose associated benchmarks: (1) Behavior metric bias, which can result from the use of metrics that do not match the structure of the behavior space. (2) Behavioral Plateaus, with varying characteristics, such that escaping them would require adaptive QD algorithms and (3) Evolvability Traps, where small variations in genotype result in large behavioral changes. The environments that we propose satisfy the properties listed above.

Recent advancements in large language models (LLMs) have led to remarkable performance across a wide range of language understanding and mathematical tasks. As a result, increasing attention has been given to assessing the true reasoning capabilities of LLMs, driving research into commonsense, numerical, logical, and qualitative reasoning. However, with the rapid progress of reasoning-focused models such as OpenAI's o1 and DeepSeek's R1, there has been a growing demand for reasoning benchmarks that can keep pace with ongoing model developments. In this paper, we introduce MastermindEval, a simple, scalable, and interpretable deductive reasoning benchmark inspired by the board game Mastermind. Our benchmark supports two evaluation paradigms: (1) agentic evaluation, in which the model autonomously plays the game, and (2) deductive reasoning evaluation, in which the model is given a pre-played game state with only one possible valid code to infer. In our experimental results we (1) find that even easy Mastermind instances are difficult for current models and (2) demonstrate that the benchmark is scalable to possibly more advanced models in the future Furthermore, we investigate possible reasons why models cannot deduce the final solution and find that current models are limited in deducing the concealed code as the number of statement to combine information from is increasing.

Recent advancements in Large Language Models (LLMs) have demonstrated their potential in planning and reasoning tasks, offering a flexible alternative to classical pathfinding algorithms. However, most existing studies focus on LLMs' independent reasoning capabilities and overlook the potential synergy between LLMs and traditional algorithms. To fill this gap, we propose a comprehensive evaluation benchmark GridRoute to assess how LLMs can take advantage of traditional algorithms. We also propose a novel hybrid prompting technique called Algorithm of Thought (AoT), which introduces traditional algorithms' guidance into prompting. Our benchmark evaluates six LLMs ranging from 7B to 72B parameters across various map sizes, assessing their performance in correctness, optimality, and efficiency in grid environments with varying sizes. Our results show that AoT significantly boosts performance across all model sizes, particularly in larger or more complex environments, suggesting a promising approach to addressing path planning challenges. Our code is open-sourced at https://github.com/LinChance/GridRoute.

Large reasoning models such as OpenAI o1 and DeepSeek-R1 have achieved remarkable performance in the domain of reasoning. A key component of their training is the incorporation of verifiable rewards within reinforcement learning (RL). However, existing reward benchmarks do not evaluate reference-based reward systems, leaving researchers with limited understanding of the accuracy of verifiers used in RL. In this paper, we introduce two benchmarks, VerifyBench and VerifyBench-Hard, designed to assess the performance of reference-based reward systems. These benchmarks are constructed through meticulous data collection and curation, followed by careful human annotation to ensure high quality. Current models still show considerable room for improvement on both VerifyBench and VerifyBench-Hard, especially smaller-scale models. Furthermore, we conduct a thorough and comprehensive analysis of evaluation results, offering insights for understanding and developing reference-based reward systems. Our proposed benchmarks serve as effective tools for guiding the development of verifier accuracy and the reasoning capabilities of models trained via RL in reasoning tasks.

How well do AI systems perform in algorithm engineering for hard optimization problems in domains such as package-delivery routing, crew scheduling, factory production planning, and power-grid balancing? We introduce ALE-Bench, a new benchmark for evaluating AI systems on score-based algorithmic programming contests. Drawing on real tasks from the AtCoder Heuristic Contests, ALE-Bench presents optimization problems that are computationally hard and admit no known exact solution. Unlike short-duration, pass/fail coding benchmarks, ALE-Bench encourages iterative solution refinement over long time horizons. Our software framework supports interactive agent architectures that leverage test-run feedback and visualizations. Our evaluation of frontier LLMs revealed that while they demonstrate high performance on specific problems, a notable gap remains compared to humans in terms of consistency across problems and long-horizon problem-solving capabilities. This highlights the need for this benchmark to foster future AI advancements.

Recent advancements in language models have led to significant improvements in mathematical reasoning across various benchmarks. However, most of these benchmarks rely on automatic evaluation methods that only compare final answers using heuristics, without verifying the underlying reasoning steps. This limitation results in false positive solutions, where models may produce correct final answers but with flawed deduction paths. In this paper, we systematically examine the prevalence of false positive solutions in mathematical problem solving for language models. We analyze the characteristics and extent of this issue across different open-source models, datasets of varying difficulty levels, and decoding strategies. Specifically, we explore how false positives influence the inference time scaling behavior of language models. Our experimental results reveal that: (1) false positive solutions persist across different models, datasets, and decoding methods, (2) sampling-based inference time scaling methods do not alleviate the problem, and (3) the pass@N evaluation metric is more susceptible to false positives, suggesting a significantly lower scaling ceiling than what automatic evaluations indicate. Additionally, we analyze specific instances of false positives and discuss potential limitations in self-improvement techniques and synthetic data generation under such conditions. Our data and code are publicly available at https://github.com/Wloner0809/False-Positives-in-Math.

With the advancement of large language models (LLMs), solving complex reasoning tasks has gained increasing attention. Inference-time computation methods (e.g., Best-of-N, beam search, et al.) are particularly valuable as they can enhance reasoning performance without modifying model parameters or requiring additional training. However, these techniques come with implementation challenges, and most existing methods remain at the proof-of-concept stage with limited practical adoption due to their computational complexity and varying effectiveness across different tasks. In this paper, we investigate and benchmark diverse inference-time computation strategies across reasoning tasks of varying complexity. Since most current methods rely on a proposer-verifier pipeline that first generates candidate solutions (e.g., reasoning solutions) and then selects the best one based on reward signals (e.g., RLHF rewards, process rewards), our research focuses on optimizing both candidate solution generation (e.g., instructing prompts, hyperparameters such as temperature and top-p) and reward mechanisms (e.g., self-evaluation, reward types). Through extensive experiments (more than 20,000 A100-80G GPU hours with over 1,000 experiments) across a variety of models (e.g., Llama, Qwen, and Mistral families) of various sizes, our ablation studies reveal that previously overlooked strategies can significantly enhance performance (e.g., tuning temperature can improve reasoning task performance by up to 5%). Furthermore, we establish a standardized benchmark for inference-time computation by systematically evaluating six representative methods across eight reasoning tasks. These findings provide a stronger foundation for future research. The code is available at https://github.com/usail-hkust/benchmark_inference_time_computation_LLM

High-quality benchmarks are the foundation for embodied AI research, enabling significant advancements in long-horizon navigation, manipulation and rearrangement tasks. However, as frontier tasks in robotics get more advanced, they require faster simulation speed, more intricate test environments, and larger demonstration datasets. To this end, we present MS-HAB, a holistic benchmark for low-level manipulation and in-home object rearrangement. First, we provide a GPU-accelerated implementation of the Home Assistant Benchmark (HAB). We support realistic low-level control and achieve over 3x the speed of previous magical grasp implementations at similar GPU memory usage. Second, we train extensive reinforcement learning (RL) and imitation learning (IL) baselines for future work to compare against. Finally, we develop a rule-based trajectory filtering system to sample specific demonstrations from our RL policies which match predefined criteria for robot behavior and safety. Combining demonstration filtering with our fast environments enables efficient, controlled data generation at scale.

Puzzlehunts are a genre of complex, multi-step puzzles lacking well-defined problem definitions. In contrast to conventional reasoning benchmarks consisting of tasks with clear instructions, puzzlehunts require models to discover the underlying problem structure from multimodal evidence and iterative reasoning, mirroring real-world domains such as scientific discovery, exploratory data analysis, or investigative problem-solving. Despite recent progress in foundation models, their performance on such open-ended settings remains largely untested. In this paper, we introduce PuzzleWorld, a large-scale benchmark of 667 puzzlehunt-style problems designed to assess step-by-step, open-ended, and creative multimodal reasoning. Each puzzle is annotated with the final solution, detailed reasoning traces, and cognitive skill labels, enabling holistic benchmarking and fine-grained diagnostic analysis. Most state-of-the-art models achieve only 1-2% final answer accuracy, with the best model solving only 14% of puzzles and reaching 40% stepwise accuracy. To demonstrate the value of our reasoning annotations, we show that fine-tuning a small model on reasoning traces improves stepwise reasoning from 4% to 11%, while training on final answers alone degrades performance to near zero. Our error analysis reveals that current models exhibit myopic reasoning, are bottlenecked by the limitations of language-based inference, and lack sketching capabilities crucial for visual and spatial reasoning. We release PuzzleWorld at https://github.com/MIT-MI/PuzzleWorld to support future work on building more general, open-ended, and creative reasoning systems.

Large language models (LLMs) have demonstrated solid zero-shot reasoning capabilities, which is reflected in their performance on the current test tasks. This calls for a more challenging benchmark requiring highly advanced reasoning ability to be solved. In this paper, we introduce such a benchmark, consisting of 191 long-form (1200 words on average) mystery narratives constructed as detective puzzles. Puzzles are sourced from the "5 Minute Mystery" platform and include a multiple-choice question for evaluation. Only 47% of humans solve a puzzle successfully on average, while the best human solvers achieve over 80% success rate. We show that GPT-3 models barely outperform random on this benchmark (with 28% accuracy) while state-of-the-art GPT-4 solves only 38% of puzzles. This indicates that there is still a significant gap in the deep reasoning abilities of LLMs and humans and highlights the need for further research in this area. Our work introduces a challenging benchmark for future studies on reasoning in language models and contributes to a better understanding of the limits of LLMs' abilities.

Large reasoning models (LRMs) have demonstrated impressive reasoning capabilities across a broad range of tasks including Olympiad-level mathematical problems, indicating evidence of their complex reasoning abilities. While many reasoning benchmarks focus on the STEM domain, the ability of LRMs to reason correctly in broader task domains remains underexplored. In this work, we introduce TTT-Bench, a new benchmark that is designed to evaluate basic strategic, spatial, and logical reasoning abilities in LRMs through a suite of four two-player Tic-Tac-Toe-style games that humans can effortlessly solve from a young age. We propose a simple yet scalable programmatic approach for generating verifiable two-player game problems for TTT-Bench. Although these games are trivial for humans, they require reasoning about the intentions of the opponent, as well as the game board's spatial configurations, to ensure a win. We evaluate a diverse set of state-of-the-art LRMs, and discover that the models that excel at hard math problems frequently fail at these simple reasoning games. Further testing reveals that our evaluated reasoning models score on average downarrow 41\% \& downarrow 5\% lower on TTT-Bench compared to MATH 500 \& AIME 2024 respectively, with larger models achieving higher performance using shorter reasoning traces, where most of the models struggle on long-term strategic reasoning situations on simple and new TTT-Bench tasks.

As large language models (LLMs) reach high scores on established mathematical benchmarks, such as GSM8K and MATH, the research community has turned to International Mathematical Olympiad (IMO) problems to push the evaluation frontier. However, existing Olympiad-level benchmarks suffer from practical constraints that introduce grading noise and potential bias, such as heterogeneous answer formats requiring model-based judges and a reliance on potentially flawed solutions. We introduce RIMO, a two-track benchmark designed to preserve peak Olympiad difficulty while eliminating this evaluation noise. The first track, RIMO-N, rewrites 335 IMO problems to admit a single, unique integer answer, allowing for deterministic correctness checking. The second track, RIMO-P, features 456 proof problems with expert-checked solutions, which are decomposed into a sequence of sub-problems to evaluate the step-by-step reasoning process via an automated grading system. Our benchmarking of ten frontier LLMs, including GPT-4o and Gemini 2.5 Flash, reveals that while these systems excel on older benchmarks, their performance drops sharply on RIMO. These results highlight a substantial gap between current LLM capabilities and actual Olympiad-level reasoning. By providing a challenging yet easy-to-evaluate suite, RIMO offers a high-resolution yardstick for future research, presenting a clear target for closing the profound reasoning gap our findings expose.

Recent advances in large language models (LLMs), particularly those enhanced through reinforced post-training, have demonstrated impressive reasoning capabilities, as exemplified by models such as OpenAI o1 and DeepSeek-R1. However, these capabilities are predominantly benchmarked on domains like mathematical problem solving and code generation -- leaving open the question of whether such reasoning skills generalize to complex, real-world scenarios. In this paper, we introduce LocationReasoner, a benchmark designed to evaluate LLMs' reasoning abilities in the context of real-world site selection, where models must identify feasible locations by reasoning over diverse and complicated spatial, environmental, and logistical constraints. The benchmark comprises over 300 carefully crafted queries of varying difficulty levels, supported by a sandbox environment with in-house tools for constraint-based location search. Extensive evaluations reveal that state-of-the-art reasoning models offer limited improvement over their non-reasoning predecessors in real-world contexts, with even the latest OpenAI o4 model failing on 30% of site selection tasks. Moreover, agentic strategies such as ReAct and Reflexion often suffer from over-reasoning, leading to worse outcomes than direct code-generation prompting. With key limitations of LLMs in holistic and non-linear reasoning highlighted, we release LocationReasoner to foster the development of LLMs and agents capable of robust, grounded reasoning in real-world decision-making tasks. Codes and data for our benchmark are available at https://github.com/miho-koda/LocationReasoner.

Computing olympiads contain some of the most challenging problems for humans, requiring complex algorithmic reasoning, puzzle solving, in addition to generating efficient code. However, it has been understudied as a domain to evaluate language models (LMs). In this paper, we introduce the USACO benchmark with 307 problems from the USA Computing Olympiad, along with high-quality unit tests, reference code, and official analyses for each problem. These resources enable us to construct and test a range of LM inference methods for competitive programming for the first time. We find GPT-4 only achieves a 8.7% pass@1 accuracy with zero-shot chain-of-thought prompting, and our best inference method improves it to 20.2% using a combination of self-reflection and retrieval over episodic knowledge. However, this is far from solving the benchmark. To better understand the remaining challenges, we design a novel human-in-the-loop study and surprisingly find that a small number of targeted hints enable GPT-4 to solve 13 out of 15 problems previously unsolvable by any model and method. Our benchmark, baseline methods, quantitative results, and qualitative analysis serve as an initial step toward LMs with grounded, creative, and algorithmic reasoning.

Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments. To address this, we introduce EscapeBench, a benchmark suite of room escape game environments designed to challenge agents with creative reasoning, unconventional tool use, and iterative problem-solving to uncover implicit goals. Our results show that current LM models, despite employing working memory and Chain-of-Thought reasoning, achieve only 15% average progress without hints, highlighting their limitations in creativity. To bridge this gap, we propose EscapeAgent, a framework designed to enhance creative reasoning through Foresight (innovative tool use) and Reflection (identifying unsolved tasks). Experiments show that EscapeAgent can execute action chains over 1,000 steps while maintaining logical coherence. It navigates and completes games with up to 40% fewer steps and hints, performs robustly across difficulty levels, and achieves higher action success rates with more efficient and innovative puzzle-solving strategies.

Large language models (LLMs) achieve good performance on challenging reasoning benchmarks, yet could also make basic reasoning mistakes. This contrasting behavior is puzzling when it comes to understanding the mechanisms behind LLMs' reasoning capabilities. One hypothesis is that the increasingly high and nearly saturated performance on common reasoning benchmarks could be due to the memorization of similar problems. In this paper, we systematically investigate this hypothesis with a quantitative measurement of memorization in reasoning tasks, using a dynamically generated logical reasoning benchmark based on Knights and Knaves (K&K) puzzles. We found that LLMs could interpolate the training puzzles (achieving near-perfect accuracy) after fine-tuning, yet fail when those puzzles are slightly perturbed, suggesting that the models heavily rely on memorization to solve those training puzzles. On the other hand, we show that while fine-tuning leads to heavy memorization, it also consistently improves generalization performance. In-depth analyses with perturbation tests, cross difficulty-level transferability, probing model internals, and fine-tuning with wrong answers suggest that the LLMs learn to reason on K&K puzzles despite training data memorization. This phenomenon indicates that LLMs exhibit a complex interplay between memorization and genuine reasoning abilities. Finally, our analysis with per-sample memorization score sheds light on how LLMs switch between reasoning and memorization in solving logical puzzles. Our code and data are available at https://memkklogic.github.io.

Thinking LLMs solve complex tasks at the expense of increased compute and overthinking on simpler problems, while non-thinking LLMs are faster and cheaper but underthink on harder reasoning problems. This has led to the development of separate thinking and non-thinking LLM variants, leaving the onus of selecting the optimal model for each query on the end user. In this work, we introduce OptimalThinkingBench, a unified benchmark that jointly evaluates overthinking and underthinking in LLMs and also encourages the development of optimally-thinking models that balance performance and efficiency. Our benchmark comprises two sub-benchmarks: OverthinkingBench, featuring simple queries in 72 domains, and UnderthinkingBench, containing 11 challenging reasoning tasks. Using novel thinking-adjusted accuracy metrics, we perform extensive evaluation of 33 different thinking and non-thinking models and show that no model is able to optimally think on our benchmark. Thinking models often overthink for hundreds of tokens on the simplest user queries without improving performance. In contrast, large non-thinking models underthink, often falling short of much smaller thinking models. We further explore several methods to encourage optimal thinking, but find that these approaches often improve on one sub-benchmark at the expense of the other, highlighting the need for better unified and optimal models in the future.

Escape rooms present a unique cognitive challenge that demands exploration-driven planning: players should actively search their environment, continuously update their knowledge based on new discoveries, and connect disparate clues to determine which elements are relevant to their objectives. Motivated by this, we introduce VisEscape, a benchmark of 20 virtual escape rooms specifically designed to evaluate AI models under these challenging conditions, where success depends not only on solving isolated puzzles but also on iteratively constructing and refining spatial-temporal knowledge of a dynamically changing environment. On VisEscape, we observed that even state-of-the-art multimodal models generally fail to escape the rooms, showing considerable variation in their levels of progress and trajectories. To address this issue, we propose VisEscaper, which effectively integrates Memory, Feedback, and ReAct modules, demonstrating significant improvements by performing 3.7 times more effectively and 5.0 times more efficiently on average.

Not yet. We present SPACE, a benchmark that systematically evaluates spatial cognition in frontier models. Our benchmark builds on decades of research in cognitive science. It evaluates large-scale mapping abilities that are brought to bear when an organism traverses physical environments, smaller-scale reasoning about object shapes and layouts, and cognitive infrastructure such as spatial attention and memory. For many tasks, we instantiate parallel presentations via text and images, allowing us to benchmark both large language models and large multimodal models. Results suggest that contemporary frontier models fall short of the spatial intelligence of animals, performing near chance level on a number of classic tests of animal cognition.

The rapid advancement of Large Language Models (LLMs) has demonstrated remarkable progress in complex reasoning tasks. However, a significant discrepancy persists between benchmark performances and real-world applications. We identify this gap as primarily stemming from current evaluation protocols and metrics, which inadequately capture the full spectrum of LLM capabilities, particularly in complex reasoning tasks where both accuracy and consistency are crucial. This work makes two key contributions. First, we introduce G-Pass@k, a novel evaluation metric that provides a continuous assessment of model performance across multiple sampling attempts, quantifying both the model's peak performance potential and its stability. Second, we present LiveMathBench, a dynamic benchmark comprising challenging, contemporary mathematical problems designed to minimize data leakage risks during evaluation. Through extensive experiments using G-Pass@k on state-of-the-art LLMs with LiveMathBench, we provide comprehensive insights into both their maximum capabilities and operational consistency. Our findings reveal substantial room for improvement in LLMs' "realistic" reasoning capabilities, highlighting the need for more robust evaluation methods. The benchmark and detailed results are available at: https://github.com/open-compass/GPassK.

Large language and multimodal models have shown remarkable successes on various benchmarks focused on specific skills such as general-purpose programming, natural language understanding, math word problem-solving, and visual question answering. However, it is unclear how well these models perform on tasks that require a combination of these skills. In this paper, we curate a novel program synthesis benchmark based on the XLogoOnline visual programming environment. The benchmark comprises 85 real-world tasks from the Mini-level of the XLogoOnline environment, each requiring a combination of different skills such as spatial planning, basic programming, and logical reasoning. Our evaluation shows that current state-of-the-art models like GPT-4V and Llama3-70B struggle to solve these tasks, achieving only 20% and 2.35% success rates. Next, we develop a fine-tuning pipeline to boost the performance of models by leveraging a large-scale synthetic training dataset with over 80000 tasks. Moreover, we showcase how emulator-driven feedback can be used to design a curriculum over training data distribution. We showcase that a fine-tuned Llama3-8B drastically outperforms GPT-4V and Llama3-70B models, and provide an in-depth analysis of the models' expertise across different skill dimensions. We will publicly release the benchmark for future research on program synthesis in visual programming.

We present PutnamBench, a new multilingual benchmark for evaluating the ability of neural theorem-provers to solve competition mathematics problems. PutnamBench consists of 1697 hand-constructed formalizations of 640 theorems sourced from the William Lowell Putnam Mathematical Competition, the premier undergraduate-level mathematics competition in North America. All the theorems have formalizations in Lean 4 and Isabelle; a substantial subset also has Coq formalizations. Proving the theorems requires significant problem-solving ability and proficiency in a broad range of topics taught in undergraduate mathematics courses. We use PutnamBench to evaluate several established neural and symbolic theorem-provers. These approaches can only solve a handful of the PutnamBench problems, establishing the benchmark as a difficult open challenge for research on neural theorem-proving. PutnamBench is available at https://github.com/trishullab/PutnamBench.

Current mathematical reasoning benchmarks for large language models (LLMs) are approaching saturation, with some achieving > 90% accuracy, and are increasingly compromised by training-set contamination. We introduce Putnam-AXIOM, a benchmark of 522 university-level competition problems drawn from the prestigious William Lowell Putnam Mathematical Competition, and Putnam-AXIOM Variation, an unseen companion set of 100 functional variants generated by programmatically perturbing variables and constants. The variation protocol produces an unlimited stream of equally difficult, unseen instances -- yielding a contamination-resilient test bed. On the Original set, OpenAI's o1-preview -- the strongest evaluated model -- scores 41.9%, but its accuracy drops by 19.6% (46.8% relative decrease) on the paired Variations. The remaining eighteen models show the same downward trend, ten of them with non-overlapping 95% confidence intervals. These gaps suggest memorization and highlight the necessity of dynamic benchmarks. We complement "boxed" accuracy with Teacher-Forced Accuracy (TFA), a lightweight metric that directly scores reasoning traces and automates natural language proof evaluations. Putnam-AXIOM therefore provides a rigorous, contamination-resilient evaluation framework for assessing advanced mathematical reasoning of LLMs. Data and evaluation code are publicly available at https://github.com/brando90/putnam-axiom.

Large language models (LLMs) have achieved impressive success on many benchmarks for mathematical reasoning. However, there is growing concern that some of this performance actually reflects dataset contamination, where data closely resembling benchmark questions leaks into the training data, instead of true reasoning ability. To investigate this claim rigorously, we commission Grade School Math 1000 (GSM1k). GSM1k is designed to mirror the style and complexity of the established GSM8k benchmark, the gold standard for measuring elementary mathematical reasoning. We ensure that the two benchmarks are comparable across important metrics such as human solve rates, number of steps in solution, answer magnitude, and more. When evaluating leading open- and closed-source LLMs on GSM1k, we observe accuracy drops of up to 13%, with several families of models (e.g., Phi and Mistral) showing evidence of systematic overfitting across almost all model sizes. At the same time, many models, especially those on the frontier, (e.g., Gemini/GPT/Claude) show minimal signs of overfitting. Further analysis suggests a positive relationship (Spearman's r^2=0.32) between a model's probability of generating an example from GSM8k and its performance gap between GSM8k and GSM1k, suggesting that many models may have partially memorized GSM8k.

While recent advances in artificial intelligence have achieved human-level performance in environments like Starcraft and Go, many physical reasoning tasks remain challenging for modern algorithms. To date, few algorithms have been evaluated on physical tasks that involve manipulating objects when movable obstacles are present and when tools must be used to perform the manipulation. To promote research on such tasks, we introduce PushWorld, an environment with simplistic physics that requires manipulation planning with both movable obstacles and tools. We provide a benchmark of more than 200 PushWorld puzzles in PDDL and in an OpenAI Gym environment. We evaluate state-of-the-art classical planning and reinforcement learning algorithms on this benchmark, and we find that these baseline results are below human-level performance. We then provide a new classical planning heuristic that solves the most puzzles among the baselines, and although it is 40 times faster than the best baseline planner, it remains below human-level performance.

In recent years, the rapid development of large reasoning models has resulted in the saturation of existing benchmarks for evaluating mathematical reasoning, highlighting the urgent need for more challenging and rigorous evaluation frameworks. To address this gap, we introduce OlymMATH, a novel Olympiad-level mathematical benchmark, designed to rigorously test the complex reasoning capabilities of LLMs. OlymMATH features 200 meticulously curated problems, each manually verified and available in parallel English and Chinese versions. The problems are systematically organized into two distinct difficulty tiers: (1) AIME-level problems (easy) that establish a baseline for mathematical reasoning assessment, and (2) significantly more challenging problems (hard) designed to push the boundaries of current state-of-the-art models. In our benchmark, these problems span four core mathematical fields, each including a verifiable numerical solution to enable objective, rule-based evaluation. Empirical results underscore the significant challenge presented by OlymMATH, with state-of-the-art models including DeepSeek-R1 and OpenAI's o3-mini demonstrating notably limited accuracy on the hard subset. Furthermore, the benchmark facilitates comprehensive bilingual assessment of mathematical reasoning abilities-a critical dimension that remains largely unaddressed in mainstream mathematical reasoning benchmarks. We release the OlymMATH benchmark at the STILL project: https://github.com/RUCAIBox/Slow_Thinking_with_LLMs.

Many challenging reasoning tasks require not just rapid, intuitive responses, but a more deliberate, multi-step approach. Recent progress in large language models (LLMs) highlights an important shift from the "System 1" way of quick reactions to the "System 2" style of reflection-and-correction problem solving. However, current benchmarks heavily rely on the final-answer accuracy, leaving much of a model's intermediate reasoning steps unexamined. This fails to assess the model's ability to reflect and rectify mistakes within the reasoning process. To bridge this gap, we introduce FINEREASON, a logic-puzzle benchmark for fine-grained evaluation of LLMs' reasoning capabilities. Each puzzle can be decomposed into atomic steps, making it ideal for rigorous validation of intermediate correctness. Building on this, we introduce two tasks: state checking, and state transition, for a comprehensive evaluation of how models assess the current situation and plan the next move. To support broader research, we also provide a puzzle training set aimed at enhancing performance on general mathematical tasks. We show that models trained on our state checking and transition data demonstrate gains in math reasoning by up to 5.1% on GSM8K.

We introduce GVGAI-LLM, a video game benchmark for evaluating the reasoning and problem-solving capabilities of large language models (LLMs). Built on the General Video Game AI framework, it features a diverse collection of arcade-style games designed to test a model's ability to handle tasks that differ from most existing LLM benchmarks. The benchmark leverages a game description language that enables rapid creation of new games and levels, helping to prevent overfitting over time. Each game scene is represented by a compact set of ASCII characters, allowing for efficient processing by language models. GVGAI-LLM defines interpretable metrics, including the meaningful step ratio, step efficiency, and overall score, to assess model behavior. Through zero-shot evaluations across a broad set of games and levels with diverse challenges and skill depth, we reveal persistent limitations of LLMs in spatial reasoning and basic planning. Current models consistently exhibit spatial and logical errors, motivating structured prompting and spatial grounding techniques. While these interventions lead to partial improvements, the benchmark remains very far from solved. GVGAI-LLM provides a reproducible testbed for advancing research on language model capabilities, with a particular emphasis on agentic behavior and contextual reasoning.

We present BenchRL-QAS, a unified benchmarking framework for reinforcement learning (RL) in quantum architecture search (QAS) across a spectrum of variational quantum algorithm tasks on 2- to 8-qubit systems. Our study systematically evaluates 9 different RL agents, including both value-based and policy-gradient methods, on quantum problems such as variational eigensolver, quantum state diagonalization, variational quantum classification (VQC), and state preparation, under both noiseless and noisy execution settings. To ensure fair comparison, we propose a weighted ranking metric that integrates accuracy, circuit depth, gate count, and training time. Results demonstrate that no single RL method dominates universally, the performance dependents on task type, qubit count, and noise conditions providing strong evidence of no free lunch principle in RL-QAS. As a byproduct we observe that a carefully chosen RL algorithm in RL-based VQC outperforms baseline VQCs. BenchRL-QAS establishes the most extensive benchmark for RL-based QAS to date, codes and experimental made publicly available for reproducibility and future advances.

Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal Large Language Models (MLLMs) inherit this reasoning potential but remain underexplored in tasks requiring both perception and logical reasoning. To address this, we introduce SEED-Bench-R1, a benchmark designed to systematically evaluate post-training methods for MLLMs in video understanding. It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions, requiring sophisticated perception and reasoning. SEED-Bench-R1 assesses generalization through a three-level hierarchy: in-distribution, cross-environment, and cross-environment-task scenarios, equipped with a large-scale training dataset with easily verifiable ground-truth answers. Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT), demonstrating RL's data efficiency and superior performance on both in-distribution and out-of-distribution tasks, even outperforming SFT on general video understanding benchmarks like LongVideoBench. Our detailed analysis reveals that RL enhances visual perception but often produces less logically coherent reasoning chains. We identify key limitations such as inconsistent reasoning and overlooked visual cues, and suggest future improvements in base model reasoning, reward modeling, and RL robustness against noisy signals.

We present AMO-Bench, an Advanced Mathematical reasoning benchmark with Olympiad level or even higher difficulty, comprising 50 human-crafted problems. Existing benchmarks have widely leveraged high school math competitions for evaluating mathematical reasoning capabilities of large language models (LLMs). However, many existing math competitions are becoming less effective for assessing top-tier LLMs due to performance saturation (e.g., AIME24/25). To address this, AMO-Bench introduces more rigorous challenges by ensuring all 50 problems are (1) cross-validated by experts to meet at least the International Mathematical Olympiad (IMO) difficulty standards, and (2) entirely original problems to prevent potential performance leakages from data memorization. Moreover, each problem in AMO-Bench requires only a final answer rather than a proof, enabling automatic and robust grading for evaluation. Experimental results across 26 LLMs on AMO-Bench show that even the best-performing model achieves only 52.4% accuracy on AMO-Bench, with most LLMs scoring below 40%. Beyond these poor performances, our further analysis reveals a promising scaling trend with increasing test-time compute on AMO-Bench. These results highlight the significant room for improving the mathematical reasoning in current LLMs. We release AMO-Bench to facilitate further research into advancing the reasoning abilities of language models. https://amo-bench.github.io/

Recent advancements in large language models (LLMs) have led to significant breakthroughs in mathematical reasoning capabilities. However, existing benchmarks like GSM8K or MATH are now being solved with high accuracy (e.g., OpenAI o1 achieves 94.8% on MATH dataset), indicating their inadequacy for truly challenging these models. To bridge this gap, we propose a comprehensive and challenging benchmark specifically designed to assess LLMs' mathematical reasoning at the Olympiad level. Unlike existing Olympiad-related benchmarks, our dataset focuses exclusively on mathematics and comprises a vast collection of 4428 competition-level problems with rigorous human annotation. These problems are meticulously categorized into over 33 sub-domains and span more than 10 distinct difficulty levels, enabling a holistic assessment of model performance in Olympiad-mathematical reasoning. Furthermore, we conducted an in-depth analysis based on this benchmark. Our experimental results show that even the most advanced models, OpenAI o1-mini and OpenAI o1-preview, struggle with highly challenging Olympiad-level problems, with 60.54% and 52.55% accuracy, highlighting significant challenges in Olympiad-level mathematical reasoning.

Complex reasoning tasks often rely on the ability to consistently and accurately apply simple rules across incremental steps, a foundational capability which we term "level-0" reasoning. To systematically evaluate this capability, we introduce L0-Bench, a language model benchmark for testing procedural correctness -- the ability to generate correct reasoning processes, complementing existing benchmarks that primarily focus on outcome correctness. Given synthetic Python functions with simple operations, L0-Bench grades models on their ability to generate step-by-step, error-free execution traces. The synthetic nature of L0-Bench enables systematic and scalable generation of test programs along various axes (e.g., number of trace steps). We evaluate a diverse array of recent closed-source and open-weight models on a baseline test set. All models exhibit degradation as the number of target trace steps increases, while larger models and reasoning-enhanced models better maintain correctness over multiple steps. Additionally, we use L0-Bench to explore test-time scaling along three dimensions: input context length, number of solutions for majority voting, and inference steps. Our results suggest substantial room to improve "level-0" reasoning and potential directions to build more reliable reasoning systems.

Deep reinforcement learning (RL) algorithms are predominantly evaluated by comparing their relative performance on a large suite of tasks. Most published results on deep RL benchmarks compare point estimates of aggregate performance such as mean and median scores across tasks, ignoring the statistical uncertainty implied by the use of a finite number of training runs. Beginning with the Arcade Learning Environment (ALE), the shift towards computationally-demanding benchmarks has led to the practice of evaluating only a small number of runs per task, exacerbating the statistical uncertainty in point estimates. In this paper, we argue that reliable evaluation in the few run deep RL regime cannot ignore the uncertainty in results without running the risk of slowing down progress in the field. We illustrate this point using a case study on the Atari 100k benchmark, where we find substantial discrepancies between conclusions drawn from point estimates alone versus a more thorough statistical analysis. With the aim of increasing the field's confidence in reported results with a handful of runs, we advocate for reporting interval estimates of aggregate performance and propose performance profiles to account for the variability in results, as well as present more robust and efficient aggregate metrics, such as interquartile mean scores, to achieve small uncertainty in results. Using such statistical tools, we scrutinize performance evaluations of existing algorithms on other widely used RL benchmarks including the ALE, Procgen, and the DeepMind Control Suite, again revealing discrepancies in prior comparisons. Our findings call for a change in how we evaluate performance in deep RL, for which we present a more rigorous evaluation methodology, accompanied with an open-source library rliable, to prevent unreliable results from stagnating the field.

Large language models (LLMs) have shown increasing capability in problem-solving and decision-making, largely based on the step-by-step chain-of-thought reasoning processes. However, it has been increasingly challenging to evaluate the reasoning capability of LLMs. Concretely, existing outcome-based benchmarks begin to saturate and become less sufficient to monitor the progress. To this end, we present a process-based benchmark MR-BEN that demands a meta reasoning skill, where LMs are asked to locate and analyse potential errors in automatically generated reasoning steps. MR-BEN is a comprehensive benchmark comprising 5,975 questions collected from human experts, covering various subjects such as physics, chemistry, logic, coding, and more. Through our designed metrics for assessing meta-reasoning on this benchmark, we identify interesting limitations and weaknesses of current LLMs (open-source and closed-source models). For example, open-source models are seemingly comparable to GPT-4 on outcome-based benchmarks, but they lag far behind on our benchmark, revealing the underlying reasoning capability gap between them. Our dataset and codes are available on https://randolph-zeng.github.io/Mr-Ben.github.io/.

Quantum optimization holds promise for addressing classically intractable combinatorial problems, yet a standardized framework for benchmarking its performance, particularly in terms of solution quality, computational speed, and scalability is still lacking. In this work, we introduce a comprehensive benchmarking framework designed to systematically evaluate a range of quantum optimization techniques against well-established NP-hard combinatorial problems. Our framework focuses on key problem classes, including the Multi-Dimensional Knapsack Problem (MDKP), Maximum Independent Set (MIS), Quadratic Assignment Problem (QAP), and Market Share Problem (MSP). Our study evaluates gate-based quantum approaches, including the Variational Quantum Eigensolver (VQE) and its CVaR-enhanced variant, alongside advanced quantum algorithms such as the Quantum Approximate Optimization Algorithm (QAOA) and its extensions. To address resource constraints, we incorporate qubit compression techniques like Pauli Correlation Encoding (PCE) and Quantum Random Access Optimization (QRAO). Experimental results, obtained from simulated quantum environments and classical solvers, provide key insights into feasibility, optimality gaps, and scalability. Our findings highlight both the promise and current limitations of quantum optimization, offering a structured pathway for future research and practical applications in quantum-enhanced decision-making.

Recent math benchmarks for large language models (LLMs) such as MathArena indicate that state-of-the-art reasoning models achieve impressive performance on mathematical competitions like AIME, with the leading model, o3-mini, achieving scores comparable to top human competitors. However, these benchmarks evaluate models solely based on final numerical answers, neglecting rigorous reasoning and proof generation which are essential for real-world mathematical tasks. To address this, we introduce the first comprehensive evaluation of full-solution reasoning for challenging mathematical problems. Using expert human annotators, we evaluated several state-of-the-art reasoning models on the six problems from the 2025 USAMO within hours of their release. Our results reveal that all tested models struggled significantly, achieving less than 5% on average. Through detailed analysis of reasoning traces, we identify the most common failure modes and find several unwanted artifacts arising from the optimization strategies employed during model training. Overall, our results suggest that current LLMs are inadequate for rigorous mathematical reasoning tasks, highlighting the need for substantial improvements in reasoning and proof generation capabilities.

LLMs and Agents have achieved impressive progress in code generation, mathematical reasoning, and scientific discovery. However, existing benchmarks primarily measure correctness, overlooking the diversity of methods behind solutions. True innovation depends not only on producing correct answers but also on the originality of the approach. We present InnoGym, the first benchmark and framework designed to systematically evaluate the innovation potential of AI agents. InnoGym introduces two complementary metrics: performance gain, which measures improvement over the best-known solutions, and novelty, which captures methodological differences from prior approaches. The benchmark includes 18 carefully curated tasks from real-world engineering and scientific domains, each standardized through resource filtering, evaluator validation, and solution collection. In addition, we provide iGym, a unified execution environment for reproducible and long-horizon evaluations. Extensive experiments show that while some agents produce novel approaches, their lack of robustness limits performance gains. These results highlight a key gap between creativity and effectiveness, underscoring the need for benchmarks that evaluate both.

In this work, we introduce a novel evaluation paradigm for Large Language Models, one that challenges them to engage in meta-reasoning. This approach addresses critical shortcomings in existing math problem-solving benchmarks, traditionally used to evaluate the cognitive capabilities of agents. Our paradigm shifts the focus from result-oriented assessments, which often overlook the reasoning process, to a more holistic evaluation that effectively differentiates the cognitive capabilities among models. For example, in our benchmark, GPT-4 demonstrates a performance ten times more accurate than GPT3-5. The significance of this new paradigm lies in its ability to reveal potential cognitive deficiencies in LLMs that current benchmarks, such as GSM8K, fail to uncover due to their saturation and lack of effective differentiation among varying reasoning abilities. Our comprehensive analysis includes several state-of-the-art math models from both open-source and closed-source communities, uncovering fundamental deficiencies in their training and evaluation approaches. This paper not only advocates for a paradigm shift in the assessment of LLMs but also contributes to the ongoing discourse on the trajectory towards Artificial General Intelligence (AGI). By promoting the adoption of meta-reasoning evaluation methods similar to ours, we aim to facilitate a more accurate assessment of the true cognitive abilities of LLMs.

Developing interactive agents that can understand language, perceive their surroundings, and act within the physical world is a long-standing goal of AI research. The Minecraft Collaborative Building Task (MCBT) (Narayan-Chen, Jayannavar, and Hockenmaier 2019), a two-player game in which an Architect (A) instructs a Builder (B) to construct a target structure in a simulated 3D Blocks World environment, offers a rich platform to work towards this goal. In this work, we focus on the Builder Action Prediction (BAP) subtask: predicting B's actions in a multimodal game context (Jayannavar, Narayan-Chen, and Hockenmaier 2020) - a challenging testbed for grounded instruction following, with limited training data. We holistically re-examine this task and introduce BAP v2 to address key challenges in evaluation, training data, and modeling. Specifically, we define an enhanced evaluation benchmark, featuring a cleaner test set and fairer, more insightful metrics that also reveal spatial reasoning as the primary performance bottleneck. To address data scarcity and to teach models basic spatial skills, we generate different types of synthetic MCBT data. We observe that current, LLM-based SOTA models trained on the human BAP dialogues fail on these simpler, synthetic BAP ones, but show that training models on this synthetic data improves their performance across the board. We also introduce a new SOTA model, Llama-CRAFTS, which leverages richer input representations, and achieves an F1 score of 53.0 on the BAP v2 task and strong performance on the synthetic data. While this result marks a notable 6 points improvement over previous work, it also underscores the task's remaining difficulty, establishing BAP v2 as a fertile ground for future research, and providing a useful measure of the spatial capabilities of current text-only LLMs in such embodied tasks.

Reward models are used throughout the post-training of language models to capture nuanced signals from preference data and provide a training target for optimization across instruction following, reasoning, safety, and more domains. The community has begun establishing best practices for evaluating reward models, from the development of benchmarks that test capabilities in specific skill areas to others that test agreement with human preferences. At the same time, progress in evaluation has not been mirrored by the effectiveness of reward models in downstream tasks -- simpler direct alignment algorithms are reported to work better in many cases. This paper introduces RewardBench 2, a new multi-skill reward modeling benchmark designed to bring new, challenging data for accuracy-based reward model evaluation -- models score about 20 points on average lower on RewardBench 2 compared to the first RewardBench -- while being highly correlated with downstream performance. Compared to most other benchmarks, RewardBench 2 sources new human prompts instead of existing prompts from downstream evaluations, facilitating more rigorous evaluation practices. In this paper, we describe our benchmark construction process and report how existing models perform on it, while quantifying how performance on the benchmark correlates with downstream use of the models in both inference-time scaling algorithms, like best-of-N sampling, and RLHF training algorithms like proximal policy optimization.

We developed a benchmark set to assess the generalization of state-of-the-art large language models on problems beyond linguistic tasks and evaluate it on a systematic progression of GPT models (GPT-3.5, GPT-4, GPT-4o, GPT-4o-mini). Using simple games like Tic-Tac-Toe, Connect Four, Battleship, and a Shape Recognition Game, all encoded in ASCII, we test strategic capabilities and spatial reasoning, core abilities any artificial intelligence would need to master for solving problems in chemistry. To probe generalization, we introduce two new games for spatial logic: LEGO Connect Language (LCL) and Guess-the-SMILES (GtS), a operationally simple chemistry benchmark. Our results show that GPT models provide meaningful responses for several tasks but, generally, perform poorly. A systematic performance progression with increased model capabilities (GPT-3.5, GPT-4, GPT-4o) is only observed for 4 out of the 7 benchmark tasks. All models consistently struggle with Battleship, LCL, and GtS. This suggests that while GPT models can emulate conversational proficiency and basic rule comprehension, they have limited generalization with respect to strategy and spatial reasoning. Particularly poor performance is observed for interpreting molecular graphs when encoded in ASCII. The results provided by our open-source benchmark suite (https://github.com/BlueVelvetSackOfGoldPotatoes/child-play{ChildPlay GitHub Repository}) caution against claims of emergent intelligence in GPT models, which appear more specialized than general.

This work investigates the reasoning and planning capabilities of foundation models and their scalability in complex, dynamic environments. We introduce PuzzlePlex, a benchmark designed to assess these capabilities through a diverse set of puzzles. PuzzlePlex consists of 15 types of puzzles, including deterministic and stochastic games of varying difficulty, as well as single-player and two-player scenarios. The PuzzlePlex framework provides a comprehensive environment for each game, and supports extensibility to generate more challenging instances as foundation models evolve. Additionally, we implement customized game-playing strategies for comparison. Building on this benchmark, we develop fine-grained metrics to measure performance and conduct an in-depth analysis of frontier foundation models across two settings: instruction-based and code-based. Furthermore, we systematically investigate their scaling limits. Our findings show that reasoning models outperform others in instruction-based settings, while code-based execution presents greater challenges but offers a scalable and efficient alternative. PuzzlePlex enables targeted evaluation and guides future improvements in reasoning, planning, and generalization for foundation models.

Spatial reasoning plays a vital role in both human cognition and machine intelligence, prompting new research into language models' (LMs) capabilities in this regard. However, existing benchmarks reveal shortcomings in evaluating qualitative spatial reasoning (QSR). These benchmarks typically present oversimplified scenarios or unclear natural language descriptions, hindering effective evaluation. We present a novel benchmark for assessing QSR in LMs, which is grounded in realistic 3D simulation data, offering a series of diverse room layouts with various objects and their spatial relationships. This approach provides a more detailed and context-rich narrative for spatial reasoning evaluation, diverging from traditional, toy-task-oriented scenarios. Our benchmark encompasses a broad spectrum of qualitative spatial relationships, including topological, directional, and distance relations. These are presented with different viewing points, varied granularities, and density of relation constraints to mimic real-world complexities. A key contribution is our logic-based consistency-checking tool, which enables the assessment of multiple plausible solutions, aligning with real-world scenarios where spatial relationships are often open to interpretation. Our benchmark evaluation of advanced LMs reveals their strengths and limitations in spatial reasoning. They face difficulties with multi-hop spatial reasoning and interpreting a mix of different view descriptions, pointing to areas for future improvement.

Recent advances in large language models (LLMs) have demonstrated notable progress on many mathematical benchmarks. However, most of these benchmarks only feature problems grounded in junior and senior high school subjects, contain only multiple-choice questions, and are confined to a limited scope of elementary arithmetic operations. To address these issues, this paper introduces an expansive benchmark suite SciBench that aims to systematically examine the reasoning capabilities required for complex scientific problem solving. SciBench contains two carefully curated datasets: an open set featuring a range of collegiate-level scientific problems drawn from mathematics, chemistry, and physics textbooks, and a closed set comprising problems from undergraduate-level exams in computer science and mathematics. Based on the two datasets, we conduct an in-depth benchmark study of two representative LLMs with various prompting strategies. The results reveal that current LLMs fall short of delivering satisfactory performance, with an overall score of merely 35.80%. Furthermore, through a detailed user study, we categorize the errors made by LLMs into ten problem-solving abilities. Our analysis indicates that no single prompting strategy significantly outperforms others and some strategies that demonstrate improvements in certain problem-solving skills result in declines in other skills. We envision that SciBench will catalyze further developments in the reasoning abilities of LLMs, thereby ultimately contributing to scientific research and discovery.

The performance of large language models (LLMs) on existing reasoning benchmarks has significantly improved over the past years. In response, we present JEEBench, a considerably more challenging benchmark dataset for evaluating the problem solving abilities of LLMs. We curate 515 challenging pre-engineering mathematics, physics and chemistry problems from the highly competitive IIT JEE-Advanced exam. Long-horizon reasoning on top of deep in-domain knowledge is essential for solving problems in this benchmark. Our evaluation on various open-source and proprietary models reveals that the highest performance, even after using techniques like self-consistency, self-refinement and chain-of-thought prompting, is less than 40%. The typical failure modes of GPT-4, the best model, are errors in algebraic manipulation, difficulty in grounding abstract concepts into mathematical equations accurately and failure in retrieving relevant domain-specific concepts. We also observe that by mere prompting, GPT-4 is unable to assess risk introduced by negative marking for incorrect answers. For this, we develop a post-hoc confidence-thresholding method over self-consistency, which enables effective response selection. We hope that our challenging benchmark will guide future re-search in problem-solving using LLMs.

We introduce RL4CO, an extensive reinforcement learning (RL) for combinatorial optimization (CO) benchmark. RL4CO employs state-of-the-art software libraries as well as best practices in implementation, such as modularity and configuration management, to be efficient and easily modifiable by researchers for adaptations of neural network architecture, environments, and algorithms. Contrary to the existing focus on specific tasks like the traveling salesman problem (TSP) for performance assessment, we underline the importance of scalability and generalization capabilities for diverse optimization tasks. We also systematically benchmark sample efficiency, zero-shot generalization, and adaptability to changes in data distributions of various models. Our experiments show that some recent state-of-the-art methods fall behind their predecessors when evaluated using these new metrics, suggesting the necessity for a more balanced view of the performance of neural CO solvers. We hope RL4CO will encourage the exploration of novel solutions to complex real-world tasks, allowing to compare with existing methods through a standardized interface that decouples the science from the software engineering. We make our library publicly available at https://github.com/kaist-silab/rl4co.

Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning, neglecting the complexities of non-verbal, multi-step visual simulation. We introduce STARE(Spatial Transformations and Reasoning Evaluation), a benchmark designed to rigorously evaluate multimodal large language models on tasks better solved through multi-step visual simulation. STARE features 4K tasks spanning foundational geometric transformations (2D and 3D), integrated spatial reasoning (cube net folding and tangram puzzles), and real-world spatial reasoning (perspective and temporal reasoning), reflecting practical cognitive challenges like object assembly, mechanical diagram interpretation, and everyday spatial navigation. Our evaluations show that models excel at reasoning over simpler 2D transformations, but perform close to random chance on more complex tasks like 3D cube net folding and tangram puzzles that require multi-step visual simulations. Humans achieve near-perfect accuracy but take considerable time (up to 28.9s) on complex tasks, significantly speeding up (down by 7.5 seconds on average) with intermediate visual simulations. In contrast, models exhibit inconsistent performance gains from visual simulations, improving on most tasks but declining in specific cases like tangram puzzles (GPT-4o, o1) and cube net folding (Claude-3.5, Gemini-2.0 Flash), indicating that models may not know how to effectively leverage intermediate visual information.

While Large Language Models (LLMs) have demonstrated significant advancements in reasoning and agent-based problem-solving, current evaluation methodologies fail to adequately assess their capabilities: existing benchmarks either rely on closed-ended questions prone to saturation and memorization, or subjective comparisons that lack consistency and rigor. In this work, we introduce HeuriGym, an agentic framework designed for evaluating heuristic algorithms generated by LLMs for combinatorial optimization problems, characterized by clearly defined objectives and expansive solution spaces. HeuriGym empowers LLMs to propose heuristics, receive evaluative feedback via code execution, and iteratively refine their solutions. We evaluate nine state-of-the-art models on nine problems across domains such as computer systems, logistics, and biology, exposing persistent limitations in tool use, planning, and adaptive reasoning. To quantify performance, we propose the Quality-Yield Index (QYI), a metric that captures both solution pass rate and quality. Even top models like GPT-o4-mini-high and Gemini-2.5-Pro attain QYI scores of only 0.6, well below the expert baseline of 1. Our open-source benchmark aims to guide the development of LLMs toward more effective and realistic problem-solving in scientific and engineering domains.

Existing benchmarks for evaluating mathematical reasoning in large language models (LLMs) rely primarily on competition problems, formal proofs, or artificially challenging questions -- failing to capture the nature of mathematics encountered in actual research environments. We introduce RealMath, a novel benchmark derived directly from research papers and mathematical forums that assesses LLMs' abilities on authentic mathematical tasks. Our approach addresses three critical challenges: sourcing diverse research-level content, enabling reliable automated evaluation through verifiable statements, and designing a continually refreshable dataset to mitigate contamination risks. Experimental results across multiple LLMs reveal surprising capabilities in handling research mathematics compared to competition problems, suggesting current models may already serve as valuable assistants for working mathematicians despite limitations on highly challenging problems. The code and dataset for RealMath are publicly available.

We propose a framework for robust evaluation of reasoning capabilities of language models, using functional variants of benchmarks. Models that solve a reasoning test should exhibit no difference in performance over the static version of a problem compared to a snapshot of the functional variant. We have rewritten the relevant fragment of the MATH benchmark into its functional variant MATH(), with functionalization of other benchmarks to follow. When evaluating current state-of-the-art models over snapshots of MATH(), we find a reasoning gap -- the percentage difference between the static and functional accuracies. We find reasoning gaps from 58.35% to 80.31% among the state-of-the-art closed and open weights models that perform well on static benchmarks, with the caveat that the gaps are likely to be smaller with more sophisticated prompting strategies. Here we show that models which anecdotally have good reasoning performance over real-world tasks, have quantifiable lower gaps, motivating the open problem of building "gap 0" models. Code for evaluation and new evaluation datasets, three MATH() snapshots, are publicly available at https://github.com/consequentai/fneval/.

Existing reasoning datasets saturate and fail to test abstract, multi-step problems, especially pathfinding and complex rule constraint satisfaction. We introduce SPaRC (Spatial Pathfinding Reasoning Challenge), a dataset of 1,000 2D grid pathfinding puzzles to evaluate spatial and symbolic reasoning, requiring step-by-step planning with arithmetic and geometric rules. Humans achieve near-perfect accuracy (98.0%; 94.5% on hard puzzles), while the best reasoning models, such as o4-mini, struggle (15.8%; 1.1% on hard puzzles). Models often generate invalid paths (>50% of puzzles for o4-mini), and reasoning tokens reveal they make errors in navigation and spatial logic. Unlike humans, who take longer on hard puzzles, models fail to scale test-time compute with difficulty. Allowing models to make multiple solution attempts improves accuracy, suggesting potential for better spatial reasoning with improved training and efficient test-time scaling methods. SPaRC can be used as a window into models' spatial reasoning limitations and drive research toward new methods that excel in abstract, multi-step problem-solving.

There is growing excitement about the potential of Language Models (LMs) to accelerate scientific discovery. Falsifying hypotheses is key to scientific progress, as it allows claims to be iteratively refined over time. This process requires significant researcher effort, reasoning, and ingenuity. Yet current benchmarks for LMs predominantly assess their ability to generate solutions rather than challenge them. We advocate for developing benchmarks that evaluate this inverse capability - creating counterexamples for subtly incorrect solutions. To demonstrate this approach, we start with the domain of algorithmic problem solving, where counterexamples can be evaluated automatically using code execution. Specifically, we introduce REFUTE, a dynamically updating benchmark that includes recent problems and incorrect submissions from programming competitions, where human experts successfully identified counterexamples. Our analysis finds that the best reasoning agents, even OpenAI o3-mini (high) with code execution feedback, can create counterexamples for only <9% of incorrect solutions in REFUTE, even though ratings indicate its ability to solve up to 48% of these problems from scratch. We hope our work spurs progress in evaluating and enhancing LMs' ability to falsify incorrect solutions - a capability that is crucial for both accelerating research and making models self-improve through reliable reflective reasoning.

Large Language Models (LLMs) have made significant strides in mathematical reasoning, underscoring the need for a comprehensive and fair evaluation of their capabilities. However, existing benchmarks often fall short, either lacking extensive coverage of undergraduate-level mathematical problems or probably suffering from test-set contamination. To address these issues, we introduce UGMathBench, a diverse and dynamic benchmark specifically designed for evaluating undergraduate-level mathematical reasoning with LLMs. UGMathBench comprises 5,062 problems across 16 subjects and 111 topics, featuring 10 distinct answer types. Each problem includes three randomized versions, with additional versions planned for release as leading open-source LLMs become saturated in UGMathBench. Furthermore, we propose two key metrics: effective accuracy (EAcc), which measures the percentage of correctly solved problems across all three versions, and reasoning gap (Delta), which assesses reasoning robustness by calculating the difference between the average accuracy across all versions and EAcc. Our extensive evaluation of 23 leading LLMs reveals that the highest EAcc achieved is 56.3\% by OpenAI-o1-mini, with large Delta values observed across different models. This highlights the need for future research aimed at developing "large reasoning models" with high EAcc and Delta = 0. We anticipate that the release of UGMathBench, along with its detailed evaluation codes, will serve as a valuable resource to advance the development of LLMs in solving mathematical problems.

Humans can directly imagine and manipulate visual images in their minds, a capability known as spatial visualization. While multi-modal Large Language Models (MLLMs) support imagination-based reasoning, spatial visualization remains insufficiently evaluated, typically embedded within broader mathematical and logical assessments. Existing evaluations often rely on IQ tests or math competitions that may overlap with training data, compromising assessment reliability. To this end, we introduce SpatialViz-Bench, a comprehensive multi-modal benchmark for spatial visualization with 12 tasks across 4 sub-abilities, comprising 1,180 automatically generated problems. Our evaluation of 33 state-of-the-art MLLMs not only reveals wide performance variations and demonstrates the benchmark's strong discriminative power, but also uncovers counter-intuitive findings: models exhibit unexpected behaviors by showing difficulty perception that misaligns with human intuition, displaying dramatic 2D-to-3D performance cliffs, and defaulting to formula derivation despite spatial tasks requiring visualization alone. SpatialVizBench empirically demonstrates that state-of-the-art MLLMs continue to exhibit deficiencies in spatial visualization tasks, thereby addressing a significant lacuna in the field. The benchmark is publicly available.

Recent large language models (LLMs) have shown indications of mathematical reasoning ability. However it has not been clear how they would fare on more challenging competition-level problems. And while self-generated verbalizations of intermediate reasoning steps (i.e., chain-of-thought prompting) have been shown to be helpful, whether LLMs can make use of helpful side information such as problem-specific hints has not been investigated before. In this paper, we propose a challenging benchmark dataset for enabling such analyses. The Concept and Hint-Annotated Math Problems (CHAMP) consists of high school math competition problems, annotated with concepts, or general math facts, and hints, or problem-specific tricks. These annotations allow us to explore the effects of additional information, such as relevant hints, misleading concepts, or related problems. This benchmark is difficult, with the best model only scoring 58.1% in standard settings. With concepts and hints, performance sometimes improves, indicating that some models can make use of such side information. We further annotate model-generated solutions for their correctness. Using this corpus, we find that models often arrive at the correct final answer through wrong reasoning steps. In addition, we test whether models are able to verify these solutions, and find that most models struggle. The dataset and code are available on the project website.

Evaluation of reasoning language models gained importance after it was observed that they can combine their existing capabilities into novel traces of intermediate steps before task completion and that the traces can sometimes help them to generalize better than past models. As reasoning becomes the next scaling dimension of large language models, careful study of their capabilities in critical tasks is needed. We show that better performance is not always caused by test-time algorithmic improvements or model sizes but also by using impactful benchmarks as curricula for learning. We call this benchmark-driven selection of AI and show its effects on DeepSeek-R1 using our sequential decision-making problem from Humanity's Last Exam. Steering development of AI by impactful benchmarks trades evaluation for learning and makes novelty of test tasks key for measuring generalization capabilities of reasoning models. Consequently, some benchmarks could be seen as curricula for training rather than unseen test sets.

Competitive programming problems increasingly serve as valuable benchmarks to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification. Yet, current coding benchmarks face limitations such as lack of exceptionally challenging problems, insufficient test case coverage, reliance on online platform APIs that limit accessibility. To address these issues, we introduce LiveOIBench, a comprehensive benchmark featuring 403 expert-curated Olympiad-level competitive programming problems, each with an average of 60 expert-designed test cases. The problems are sourced directly from 72 official Informatics Olympiads in different regions conducted between 2023 and 2025. LiveOIBench distinguishes itself through four key features: (1) meticulously curated high-quality tasks with detailed subtask rubrics and extensive private test cases; (2) direct integration of elite contestant performance data to enable informative comparison against top-performing humans; (3) planned continuous, contamination-free updates from newly released Olympiad problems; and (4) a self-contained evaluation system facilitating offline and easy-to-reproduce assessments. Benchmarking 32 popular general-purpose and reasoning LLMs, we find that GPT-5 achieves a notable 81.76th percentile, a strong result that nonetheless falls short of top human contestant performance, who usually place above 90th. In contrast, among open-weight reasoning models, GPT-OSS-120B achieves only a 60th percentile, underscoring significant capability disparities from frontier closed models. Detailed analyses indicate that robust reasoning models prioritize precise problem analysis over excessive exploration, suggesting future models should emphasize structured analysis and minimize unnecessary exploration. All data, code, and leaderboard results will be made publicly available on our website.

We introduce PRISM-Bench, a benchmark of puzzle-based visual challenges designed to evaluate not only whether models can solve problems, but how their reasoning unfolds. Unlike prior evaluations that measure only final-answer accuracy, PRISM-Bench introduces a diagnostic task: given a visual puzzle and a step-by-step chain-of-thought (CoT) containing exactly one error, models must identify the first incorrect step. This setting enables fine-grained assessment of logical consistency, error detection, and visual reasoning. The puzzles in PRISM-Bench require multi-step symbolic, geometric, and analogical reasoning, resisting shortcuts based on superficial pattern matching. Evaluations across state-of-the-art MLLMs reveal a persistent gap between fluent generation and faithful reasoning: models that produce plausible CoTs often fail to locate simple logical faults. By disentangling answer generation from reasoning verification, PRISM-Bench offers a sharper lens on multimodal reasoning competence and underscores the need for diagnostic evaluation protocols in the development of trustworthy MLLMs.

Evaluating the reasoning abilities of large language models (LLMs) is challenging. Existing benchmarks often depend on static datasets, which are vulnerable to data contamination and may get saturated over time, or on binary live human feedback that conflates reasoning with other abilities. As the most prominent dynamic benchmark, Chatbot Arena evaluates open-ended questions in real-world settings, but lacks the granularity in assessing specific reasoning capabilities. We introduce GameArena, a dynamic benchmark designed to evaluate LLM reasoning capabilities through interactive gameplay with humans. GameArena consists of three games designed to test specific reasoning capabilities (e.g., deductive and inductive reasoning), while keeping participants entertained and engaged. We analyze the gaming data retrospectively to uncover the underlying reasoning processes of LLMs and measure their fine-grained reasoning capabilities. We collect over 2000 game sessions and provide detailed assessments of various reasoning capabilities for five state-of-the-art LLMs. Our user study with 100 participants suggests that GameArena improves user engagement compared to Chatbot Arena. For the first time, GameArena enables the collection of step-by-step LLM reasoning data in the wild.

Reward models are key in reinforcement learning from human feedback (RLHF) systems, aligning the model behavior with human preferences. Particularly in the math domain, there have been plenty of studies using reward models to align policies for improving reasoning capabilities. Recently, as the importance of reward models has been emphasized, RewardBench is proposed to understand their behavior. However, we figure out that the math subset of RewardBench has different representations between chosen and rejected completions, and relies on a single comparison, which may lead to unreliable results as it only see an isolated case. Therefore, it fails to accurately present the robustness of reward models, leading to a misunderstanding of its performance and potentially resulting in reward hacking. In this work, we introduce a new design for reliable evaluation of reward models, and to validate this, we construct RewardMATH, a benchmark that effectively represents the robustness of reward models in mathematical reasoning tasks. We demonstrate that the scores on RewardMATH strongly correlate with the results of optimized policy and effectively estimate reward overoptimization, whereas the existing benchmark shows almost no correlation. The results underscore the potential of our design to enhance the reliability of evaluation, and represent the robustness of reward model. We make our code and data publicly available.

Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenarios and predominant RL training paradigms rely on rule-based or reference-based rewards, which impose two critical limitations: 1) the dependence on finely annotated reference answer to attain rewards; and 2) the requirement for constrained output format. These limitations fundamentally hinder further RL data scaling and sustained enhancement of model reasoning performance. To address these limitations, we propose a comprehensive framework for evaluating and improving the performance of reward models in complex reasoning scenarios. We first present a reasoning-oriented benchmark (Libra Bench), systematically constructed from a diverse collection of challenging mathematical problems and advanced reasoning models, to address the limitations of existing reward model benchmarks in reasoning scenarios. We further introduce a novel approach for improving the generative reward model via learning-to-think methodologies. Based on the proposed approach, we develop Libra-RM series, a collection of generative reward models with reasoning capabilities that achieve state-of-the-art results on various benchmarks. Comprehensive downstream experiments are conducted and the experimental results demonstrate the correlation between our Libra Bench and downstream application, and the potential of Libra-RM to further improve reasoning models with unlabeled data.

Prior research works have evaluated quantized LLMs using limited metrics such as perplexity or a few basic knowledge tasks and old datasets. Additionally, recent large-scale models such as Llama 3.1 with up to 405B have not been thoroughly examined. This paper evaluates the performance of instruction-tuned LLMs across various quantization methods (GPTQ, AWQ, SmoothQuant, and FP8) on models ranging from 7B to 405B. Using 13 benchmarks, we assess performance across six task types: commonsense Q\&A, knowledge and language understanding, instruction following, hallucination detection, mathematics, and dialogue. Our key findings reveal that (1) quantizing a larger LLM to a similar size as a smaller FP16 LLM generally performs better across most benchmarks, except for hallucination detection and instruction following; (2) performance varies significantly with different quantization methods, model size, and bit-width, with weight-only methods often yielding better results in larger models; (3) task difficulty does not significantly impact accuracy degradation due to quantization; and (4) the MT-Bench evaluation method has limited discriminatory power among recent high-performing LLMs.

Large Language Models (LLMs) trained via Reinforcement Learning (RL) have recently achieved impressive results on reasoning benchmarks. Yet, growing evidence shows that these models often generate longer but ineffective chains of thought (CoTs), calling into question whether benchmark gains reflect real reasoning improvements. We present new evidence of overthinking, where models disregard correct solutions even when explicitly provided, instead continuing to generate unnecessary reasoning steps that often lead to incorrect conclusions. Experiments on three state-of-the-art models using the AIME2024 math benchmark reveal critical limitations in these models ability to integrate corrective information, posing new challenges for achieving robust and interpretable reasoning.

High-quality mathematical and logical datasets with verifiable answers are essential for strengthening the reasoning capabilities of large language models (LLMs). While recent data augmentation techniques have facilitated the creation of large-scale benchmarks, existing LLM-generated datasets often suffer from limited reliability, diversity, and scalability. To address these challenges, we introduce PuzzleClone, a formal framework for synthesizing verifiable data at scale using Satisfiability Modulo Theories (SMT). Our approach features three key innovations: (1) encoding seed puzzles into structured logical specifications, (2) generating scalable variants through systematic variable and constraint randomization, and (3) ensuring validity via a reproduction mechanism. Applying PuzzleClone, we construct a curated benchmark comprising over 83K diverse and programmatically validated puzzles. The generated puzzles span a wide spectrum of difficulty and formats, posing significant challenges to current state-of-the-art models. We conduct post training (SFT and RL) on PuzzleClone datasets. Experimental results show that training on PuzzleClone yields substantial improvements not only on PuzzleClone testset but also on logic and mathematical benchmarks. Post training raises PuzzleClone average from 14.4 to 56.2 and delivers consistent improvements across 7 logic and mathematical benchmarks up to 12.5 absolute percentage points (AMC2023 from 52.5 to 65.0). Our code and data are available at https://github.com/puzzleclone.

A significant challenge for robot learning research is our ability to accurately measure and compare the performance of robot policies. Benchmarking in robotics is historically challenging due to the stochasticity, reproducibility, and time-consuming nature of real-world rollouts. This challenge is exacerbated for recent generalist policies, which has to be evaluated across a wide variety of scenes and tasks. Evaluation in simulation offers a scalable complement to real world evaluations, but the visual and physical domain gap between existing simulation benchmarks and the real world has made them an unreliable signal for policy improvement. Furthermore, building realistic and diverse simulated environments has traditionally required significant human effort and expertise. To bridge the gap, we introduce Policy Evaluation and Environment Reconstruction in Simulation (PolaRiS), a scalable real-to-sim framework for high-fidelity simulated robot evaluation. PolaRiS utilizes neural reconstruction methods to turn short video scans of real-world scenes into interactive simulation environments. Additionally, we develop a simple simulation data co-training recipe that bridges remaining real-to-sim gaps and enables zero-shot evaluation in unseen simulation environments. Through extensive paired evaluations between simulation and the real world, we demonstrate that PolaRiS evaluations provide a much stronger correlation to real world generalist policy performance than existing simulated benchmarks. Its simplicity also enables rapid creation of diverse simulated environments. As such, this work takes a step towards distributed and democratized evaluation for the next generation of robotic foundation models.

Advances in Large Language Models (LLMs) have sparked interest in their ability to solve Olympiad-level math problems. However, the training and evaluation of these models are constrained by the limited size and quality of available datasets, as creating large-scale data for such advanced problems requires extensive effort from human experts. In addition, current benchmarks are prone to contamination, leading to unreliable evaluations. In this paper, we present an automated pipeline that leverages the rich resources of the Art of Problem Solving (AoPS) forum, which predominantly features Olympiad-level problems and community-driven solutions. Using open-source LLMs, we develop a method to extract question-answer pairs from the forum, resulting in AoPS-Instruct, a dataset of more than 600,000 high-quality QA pairs. Our experiments demonstrate that fine-tuning LLMs on AoPS-Instruct improves their reasoning abilities across various benchmarks. Moreover, we build an automatic pipeline that introduces LiveAoPSBench, an evolving evaluation set with timestamps, derived from the latest forum data, providing a contamination-resistant benchmark for assessing LLM performance. Notably, we observe a significant decline in LLM performance over time, suggesting their success on older examples may stem from pre-training exposure rather than true reasoning ability. Our work presents a scalable approach to creating and maintaining large-scale, high-quality datasets for advanced math reasoning, offering valuable insights into the capabilities and limitations of LLMs in this domain. Our benchmark and code is available at https://github.com/DSL-Lab/aops

The effectiveness of Large Language Models (LLMs) is heavily influenced by the reasoning strategies, or styles of thought, employed in their prompts. However, the interplay between these reasoning styles, model architecture, and task type remains poorly understood. To address this, we introduce StyleBench, a comprehensive benchmark for systematically evaluating reasoning styles across diverse tasks and models. We assess five representative reasoning styles, including Chain of Thought (CoT), Tree of Thought (ToT), Algorithm of Thought (AoT), Sketch of Thought (SoT), and Chain-of-Draft (CoD) on five reasoning tasks, using 15 open-source models from major families (LLaMA, Qwen, Mistral, Gemma, GPT-OSS, Phi, and DeepSeek) ranging from 270M to 120B parameters. Our large-scale analysis reveals that no single style is universally optimal. We demonstrate that strategy efficacy is highly contingent on both model scale and task type: search-based methods (AoT, ToT) excel in open-ended problems but require large-scale models, while concise styles (SoT, CoD) achieve radical efficiency gains on well-defined tasks. Furthermore, we identify key behavioral patterns: smaller models frequently fail to follow output instructions and default to guessing, while reasoning robustness emerges as a function of scale. Our findings offer a crucial roadmap for selecting optimal reasoning strategies based on specific constraints, we open source the benchmark in https://github.com/JamesJunyuGuo/Style_Bench.

Evaluating the pedagogical capabilities of AI-based tutoring models is critical for making guided progress in the field. Yet, we lack a reliable, easy-to-use, and simple-to-run evaluation that reflects the pedagogical abilities of models. To fill this gap, we present MathTutorBench, an open-source benchmark for holistic tutoring model evaluation. MathTutorBench contains a collection of datasets and metrics that broadly cover tutor abilities as defined by learning sciences research in dialog-based teaching. To score the pedagogical quality of open-ended teacher responses, we train a reward model and show it can discriminate expert from novice teacher responses with high accuracy. We evaluate a wide set of closed- and open-weight models on MathTutorBench and find that subject expertise, indicated by solving ability, does not immediately translate to good teaching. Rather, pedagogy and subject expertise appear to form a trade-off that is navigated by the degree of tutoring specialization of the model. Furthermore, tutoring appears to become more challenging in longer dialogs, where simpler questioning strategies begin to fail. We release the benchmark, code, and leaderboard openly to enable rapid benchmarking of future models.

Large Language Models (LLMs) have shown significant promise in automated theorem proving, yet progress is often constrained by the scarcity of diverse and high-quality formal language data. To address this issue, we introduce Spark-Prover-X1, a 7B parameter model trained via an three-stage framework designed to unlock the reasoning potential of more accessible and moderately-sized LLMs. The first stage infuses deep knowledge through continuous pre-training on a broad mathematical corpus, enhanced by a suite of novel data tasks. Key innovation is a "CoT-augmented state prediction" task to achieve fine-grained reasoning. The second stage employs Supervised Fine-tuning (SFT) within an expert iteration loop to specialize both the Spark-Prover-X1-7B and Spark-Formalizer-X1-7B models. Finally, a targeted round of Group Relative Policy Optimization (GRPO) is applied to sharpen the prover's capabilities on the most challenging problems. To facilitate robust evaluation, particularly on problems from real-world examinations, we also introduce ExamFormal-Bench, a new benchmark dataset of 402 formal problems. Experimental results demonstrate that Spark-Prover achieves state-of-the-art performance among similarly-sized open-source models within the "Whole-Proof Generation" paradigm. It shows exceptional performance on difficult competition benchmarks, notably solving 27 problems on PutnamBench (pass@32) and achieving 24.0\% on CombiBench (pass@32). Our work validates that this diverse training data and progressively refined training pipeline provides an effective path for enhancing the formal reasoning capabilities of lightweight LLMs. We will release both Spark-Prover-X1-7B and Spark-Formalizer-X1-7B, along with the ExamFormal-Bench dataset, in the near future.

Reasoning is a fundamental capability for solving complex multi-step problems, particularly in visual contexts where sequential step-wise understanding is essential. Existing approaches lack a comprehensive framework for evaluating visual reasoning and do not emphasize step-wise problem-solving. To this end, we propose a comprehensive framework for advancing step-by-step visual reasoning in large language models (LMMs) through three key contributions. First, we introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks. The benchmark presents a diverse set of challenges with eight different categories ranging from complex visual perception to scientific reasoning with over 4k reasoning steps in total, enabling robust evaluation of LLMs' abilities to perform accurate and interpretable visual reasoning across multiple steps. Second, we propose a novel metric that assesses visual reasoning quality at the granularity of individual steps, emphasizing both correctness and logical coherence. The proposed metric offers deeper insights into reasoning performance compared to traditional end-task accuracy metrics. Third, we present a new multimodal visual reasoning model, named LlamaV-o1, trained using a multi-step curriculum learning approach, where tasks are progressively organized to facilitate incremental skill acquisition and problem-solving. The proposed LlamaV-o1 is designed for multi-step reasoning and learns step-by-step through a structured training paradigm. Extensive experiments show that our LlamaV-o1 outperforms existing open-source models and performs favorably against close-source proprietary models. Compared to the recent Llava-CoT, our LlamaV-o1 achieves an average score of 67.3 with an absolute gain of 3.8\% across six benchmarks while being 5 times faster during inference scaling. Our benchmark, model, and code are publicly available.

Current benchmarks for evaluating Vision Language Models (VLMs) often fall short in thoroughly assessing model abilities to understand and process complex visual and textual content. They typically focus on simple tasks that do not require deep reasoning or the integration of multiple data modalities to solve an original problem. To address this gap, we introduce the PARROT-360V Benchmark, a novel and comprehensive benchmark featuring 2487 challenging visual puzzles designed to test VLMs on complex visual reasoning tasks. We evaluated leading models: GPT-4o, Claude-3.5-Sonnet, and Gemini-1.5-Pro, using PARROT-360V to assess their capabilities in combining visual clues with language skills to solve tasks in a manner akin to human problem-solving. Our findings reveal a notable performance gap: state-of-the-art models scored between 28 to 56 percentage on our benchmark, significantly lower than their performance on popular benchmarks. This underscores the limitations of current VLMs in handling complex, multi-step reasoning tasks and highlights the need for more robust evaluation frameworks to advance the field.

Large Language Models (LLMs) have demonstrated remarkable performance in solving math problems, a hallmark of human intelligence. Despite high success rates on current benchmarks; however, these often feature simple problems with only one or two unknowns, which do not sufficiently challenge their reasoning capacities. This paper introduces a novel benchmark, BeyondX, designed to address these limitations by incorporating problems with multiple unknowns. Recognizing the challenges in proposing multi-unknown problems from scratch, we developed BeyondX using an innovative automated pipeline that progressively increases complexity by expanding the number of unknowns in simpler problems. Empirical study on BeyondX reveals that the performance of existing LLMs, even those fine-tuned specifically on math tasks, significantly decreases as the number of unknowns increases - with a performance drop of up to 70\% observed in GPT-4. To tackle these challenges, we propose the Formulate-and-Solve strategy, a generalized prompting approach that effectively handles problems with an arbitrary number of unknowns. Our findings reveal that this strategy not only enhances LLM performance on the BeyondX benchmark but also provides deeper insights into the computational limits of LLMs when faced with more complex mathematical challenges.

In this paper, we present the LingOly benchmark, a novel benchmark for advanced reasoning abilities in large language models. Using challenging Linguistic Olympiad puzzles, we evaluate (i) capabilities for in-context identification and generalisation of linguistic patterns in very low-resource or extinct languages, and (ii) abilities to follow complex task instructions. The LingOly benchmark covers more than 90 mostly low-resource languages, minimising issues of data contamination, and contains 1,133 problems across 6 formats and 5 levels of human difficulty. We assess performance with both direct accuracy and comparison to a no-context baseline to penalise memorisation. Scores from 11 state-of-the-art LLMs demonstrate the benchmark to be challenging, and models perform poorly on the higher difficulty problems. On harder problems, even the top model only achieved 35.3% accuracy, 21.7% improvement over the no-context baseline. Large closed models typically outperform open models, and in general, the higher resource the language, the better the scores. These results indicate, in absence of memorisation, true multi-step out-of-domain reasoning remains a challenge for current language models.

Memory is crucial for enabling agents to tackle complex tasks with temporal and spatial dependencies. While many reinforcement learning (RL) algorithms incorporate memory, the field lacks a universal benchmark to assess an agent's memory capabilities across diverse scenarios. This gap is particularly evident in tabletop robotic manipulation, where memory is essential for solving tasks with partial observability and ensuring robust performance, yet no standardized benchmarks exist. To address this, we introduce MIKASA (Memory-Intensive Skills Assessment Suite for Agents), a comprehensive benchmark for memory RL, with three key contributions: (1) we propose a comprehensive classification framework for memory-intensive RL tasks, (2) we collect MIKASA-Base - a unified benchmark that enables systematic evaluation of memory-enhanced agents across diverse scenarios, and (3) we develop MIKASA-Robo - a novel benchmark of 32 carefully designed memory-intensive tasks that assess memory capabilities in tabletop robotic manipulation. Our contributions establish a unified framework for advancing memory RL research, driving the development of more reliable systems for real-world applications. The code is available at https://sites.google.com/view/memorybenchrobots/.

As models become increasingly sophisticated, conventional algorithm benchmarks are increasingly saturated, underscoring the need for more challenging benchmarks to guide future improvements in algorithmic reasoning. This paper introduces OIBench, a high-quality, private, and challenging olympiad-level informatics dataset comprising 250 carefully curated original problems. We detail the construction methodology of the benchmark, ensuring a comprehensive assessment across various programming paradigms and complexities, and we demonstrate its contamination-resistant properties via experiments. We propose Time/Space Completion Curves for finer-grained efficiency analysis and enable direct human-model comparisons through high-level participant evaluations. Our experiments reveal that while open-source models lag behind closed-source counterparts, current SOTA models already outperform most human participants in both correctness and efficiency, while still being suboptimal compared to the canonical solutions. By releasing OIBench as a fully open-source resource (https://huggingface.co/datasets/AGI-Eval/OIBench), we hope this benchmark will contribute to advancing code reasoning capabilities for future LLMs.

Large language models (LLMs) have significantly advanced natural language understanding and demonstrated strong problem-solving abilities. Despite these successes, most LLMs still struggle with solving mathematical problems due to the intricate reasoning required. This paper investigates the mathematical problem-solving capabilities of LLMs using the newly developed "MathOdyssey" dataset. The dataset includes diverse mathematical problems at high school and university levels, created by experts from notable institutions to rigorously test LLMs in advanced problem-solving scenarios and cover a wider range of subject areas. By providing the MathOdyssey dataset as a resource to the AI community, we aim to contribute to the understanding and improvement of AI capabilities in complex mathematical problem-solving. We conduct benchmarking on open-source models, such as Llama-3 and DBRX-Instruct, and closed-source models from the GPT series and Gemini models. Our results indicate that while LLMs perform well on routine and moderately difficult tasks, they face significant challenges with Olympiad-level problems and complex university-level questions. Our analysis shows a narrowing performance gap between open-source and closed-source models, yet substantial challenges remain, particularly with the most demanding problems. This study highlights the ongoing need for research to enhance the mathematical reasoning of LLMs. The dataset, results, and code are publicly available.

We present miniF2F, a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving. The miniF2F benchmark currently targets Metamath, Lean, Isabelle (partially) and HOL Light (partially) and consists of 488 problem statements drawn from the AIME, AMC, and the International Mathematical Olympiad (IMO), as well as material from high-school and undergraduate mathematics courses. We report baseline results using GPT-f, a neural theorem prover based on GPT-3 and provide an analysis of its performance. We intend for miniF2F to be a community-driven effort and hope that our benchmark will help spur advances in neural theorem proving.

Current evaluation paradigms for large language models (LLMs) represent a critical blind spot in AI research--relying on opaque numerical metrics that conceal fundamental limitations in spatial reasoning while providing no intuitive understanding of model capabilities. This deficiency creates a dangerous disconnect between reported performance and practical abilities, particularly for applications requiring physical world understanding. We introduce LTD-Bench, a breakthrough benchmark that transforms LLM evaluation from abstract scores to directly observable visual outputs by requiring models to generate drawings through dot matrices or executable code. This approach makes spatial reasoning limitations immediately apparent even to non-experts, bridging the fundamental gap between statistical performance and intuitive assessment. LTD-Bench implements a comprehensive methodology with complementary generation tasks (testing spatial imagination) and recognition tasks (assessing spatial perception) across three progressively challenging difficulty levels, methodically evaluating both directions of the critical language-spatial mapping. Our extensive experiments with state-of-the-art models expose an alarming capability gap: even LLMs achieving impressive results on traditional benchmarks demonstrate profound deficiencies in establishing bidirectional mappings between language and spatial concept--a fundamental limitation that undermines their potential as genuine world models. Furthermore, LTD-Bench's visual outputs enable powerful diagnostic analysis, offering a potential approach to investigate model similarity.

Large language models (LLMs) with Chain-of-Thought (CoT) prompting achieve strong reasoning but often produce unnecessarily long explanations, increasing cost and sometimes reducing accuracy. Fair comparison of efficiency-oriented approaches is hindered by fragmented evaluation practices. We introduce EffiReason-Bench, a unified benchmark for rigorous cross-paradigm evaluation of efficient reasoning methods across three categories: Reasoning Blueprints, Dynamic Execution, and Post-hoc Refinement. To enable step-by-step evaluation, we construct verified CoT annotations for CommonsenseQA and LogiQA via a pipeline that enforces standardized reasoning structures, comprehensive option-wise analysis, and human verification. We evaluate 7 methods across 6 open-source LLMs (1B-70B) on 4 datasets spanning mathematics, commonsense, and logic, and propose the E3-Score, a principled metric inspired by economic trade-off modeling that provides smooth, stable evaluation without discontinuities or heavy reliance on heuristics. Experiments show that no single method universally dominates; optimal strategies depend on backbone scale, task complexity, and architecture.

In this paper, we introduce OSUniverse: a benchmark of complex, multimodal desktop-oriented tasks for advanced GUI-navigation AI agents that focuses on ease of use, extensibility, comprehensive coverage of test cases, and automated validation. We divide the tasks in increasing levels of complexity, from basic precision clicking to multistep, multiapplication tests requiring dexterity, precision, and clear thinking from the agent. In version one of the benchmark, presented here, we have calibrated the complexity of the benchmark test cases to ensure that the SOTA (State of the Art) agents (at the time of publication) do not achieve results higher than 50%, while the average white collar worker can perform all these tasks with perfect accuracy. The benchmark can be scored manually, but we also introduce an automated validation mechanism that has an average error rate less than 2%. Therefore, this benchmark presents solid ground for fully automated measuring of progress, capabilities and the effectiveness of GUI-navigation AI agents over the short and medium-term horizon. The source code of the benchmark is available at https://github.com/agentsea/osuniverse.

As machine intelligence evolves, the need to test and compare the problem-solving abilities of different AI models grows. However, current benchmarks are often overly simplistic, allowing models to perform uniformly well, making it difficult to distinguish their capabilities. Additionally, benchmarks typically rely on static question-answer pairs, which models might memorize or guess. To address these limitations, we introduce the Dynamic Intelligence Assessment (DIA), a novel methodology for testing AI models using dynamic question templates and improved metrics across multiple disciplines such as mathematics, cryptography, cybersecurity, and computer science. The accompanying DIA-Bench dataset, which includes 150 diverse and challenging task templates with mutable parameters, is presented in various formats such as text, PDFs, compiled binaries, and visual puzzles. Our framework introduces four new metrics to assess a model's reliability and confidence across multiple attempts. These metrics revealed that even simple questions are frequently answered incorrectly when posed in varying forms, highlighting significant gaps in models' reliability. Notably, models like GPT-4o tended to overestimate their mathematical abilities, while ChatGPT-4o demonstrated better decision-making and performance through effective tool usage. We evaluated eight state-of-the-art large language models (LLMs) using DIA-Bench, showing that current models struggle with complex tasks and often display unexpectedly low confidence, even with simpler questions. The DIA framework sets a new standard for assessing not only problem-solving but also a model's adaptive intelligence and ability to assess its own limitations. The dataset is publicly available on our project's website.

We propose a new benchmark evaluating the performance of multimodal large language models on rebus puzzles. The dataset covers 333 original examples of image-based wordplay, cluing 13 categories such as movies, composers, major cities, and food. To achieve good performance on the benchmark of identifying the clued word or phrase, models must combine image recognition and string manipulation with hypothesis testing, multi-step reasoning, and an understanding of human cognition, making for a complex, multimodal evaluation of capabilities. We find that proprietary models such as GPT-4V and Gemini Pro significantly outperform all other tested models. However, even the best model has a final accuracy of just 24%, highlighting the need for substantial improvements in reasoning. Further, models rarely understand all parts of a puzzle, and are almost always incapable of retroactively explaining the correct answer. Our benchmark can therefore be used to identify major shortcomings in the knowledge and reasoning of multimodal large language models.

Large language models (LLMs) have demonstrated impressive performance on reasoning tasks, including mathematical reasoning. However, the current evaluation mostly focuses on carefully constructed benchmarks and neglects the consideration of real-world reasoning problems that present missing or contradictory conditions, known as ill-defined problems. To further study this problem, we develop a largescale benchmark called Problems with Missing and Contradictory conditions ( PMC) containing over 5,000 validated ill-defined mathematical problems. Our preliminary experiments through PMC reveal two challenges about existing methods: (1) traditional methods exhibit a trade-off between solving accuracy and rejection capabilities, and (2) formal methods struggle with modeling complex problems. To address these challenges, We develop Variable-Constraint Search (VCSEARCH), a trainingfree framework that leverages formal language to detect ill-defined problems, where a variableconstraint pair search strategy is incorporated to improve the modeling capability of formal language. Extensive experiments demonstrate that VCSEARCH improves the accuracy of identifying unsolvable problems by at least 12% across different LLMs, thus achieving stronger robust mathematical reasoning ability.

Imagine observing someone scratching their arm; to understand why, additional context would be necessary. However, spotting a mosquito nearby would immediately offer a likely explanation for the person's discomfort, thereby alleviating the need for further information. This example illustrates how subtle visual cues can challenge our cognitive skills and demonstrates the complexity of interpreting visual scenarios. To study these skills, we present Visual Riddles, a benchmark aimed to test vision and language models on visual riddles requiring commonsense and world knowledge. The benchmark comprises 400 visual riddles, each featuring a unique image created by a variety of text-to-image models, question, ground-truth answer, textual hint, and attribution. Human evaluation reveals that existing models lag significantly behind human performance, which is at 82\% accuracy, with Gemini-Pro-1.5 leading with 40\% accuracy. Our benchmark comes with automatic evaluation tasks to make assessment scalable. These findings underscore the potential of Visual Riddles as a valuable resource for enhancing vision and language models' capabilities in interpreting complex visual scenarios.

With the advent of DeepSeek-R1, a new wave of reinforcement learning (RL) methods has emerged that seem to unlock stronger mathematical reasoning. However, a closer look at the open-source ecosystem reveals a critical limitation: with sufficiently many draws (e.g., pass@1024), many existing base models already solve nearly all questions on widely used math benchmarks such as MATH-500 and AIME 2024. This suggests that the RL fine-tuning methods prevalent in the LLM reasoning literature largely sharpen existing solution modes rather than discovering entirely new ones. Such sharpening stands in contrast to the broader promise of RL: to foster exploration and to acquire new skills. To move beyond this plateau, we introduce MATH-Beyond (MATH-B), a benchmark deliberately constructed to defeat common open-source models of up to 8B parameters even under large sampling budgets. Improving performance on our benchmark via RL requires methods that learn to reason in ways that go beyond base model capabilities in repeated sampling. Since the problems are drawn from subsets of DAPO-Math-17K and DeepScaleR datasets, they remain topically equivalent to standard high-school math. Validating our premise, RL fine-tuned models such as Nemotron-Research-Reasoning-Qwen-1.5B and DeepScaleR-1.5B-Preview perform poorly on MATH-B at pass@1024, showing how existing approaches fall short on tackling harder instances. We hope MATH-B will catalyze exploration-driven RL approaches that elicit deeper reasoning capabilities. We release MATH-B at https://huggingface.co/datasets/brendel-group/MATH-Beyond.

Shojaee et al. (2025) report that Large Reasoning Models (LRMs) exhibit "accuracy collapse" on planning puzzles beyond certain complexity thresholds. We demonstrate that their findings primarily reflect experimental design limitations rather than fundamental reasoning failures. Our analysis reveals three critical issues: (1) Tower of Hanoi experiments systematically exceed model output token limits at reported failure points, with models explicitly acknowledging these constraints in their outputs; (2) The authors' automated evaluation framework fails to distinguish between reasoning failures and practical constraints, leading to misclassification of model capabilities; (3) Most concerningly, their River Crossing benchmarks include mathematically impossible instances for N > 5 due to insufficient boat capacity, yet models are scored as failures for not solving these unsolvable problems. When we control for these experimental artifacts, by requesting generating functions instead of exhaustive move lists, preliminary experiments across multiple models indicate high accuracy on Tower of Hanoi instances previously reported as complete failures. These findings highlight the importance of careful experimental design when evaluating AI reasoning capabilities.

Understanding Rebus Puzzles (Rebus Puzzles use pictures, symbols, and letters to represent words or phrases creatively) requires a variety of skills such as image recognition, cognitive skills, commonsense reasoning, multi-step reasoning, image-based wordplay, etc., making this a challenging task for even current Vision-Language Models. In this paper, we present left|,circlearrowright,text{BUS},right|, a large and diverse benchmark of 1,333 English Rebus Puzzles containing different artistic styles and levels of difficulty, spread across 18 categories such as food, idioms, sports, finance, entertainment, etc. We also propose RebusDescProgICE, a model-agnostic framework which uses a combination of an unstructured description and code-based, structured reasoning, along with better, reasoning-based in-context example selection, improving the performance of Vision-Language Models on left|,circlearrowright,text{BUS},right| by 2.1-4.1% and 20-30% using closed-source and open-source models respectively compared to Chain-of-Thought Reasoning.

Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while another critical component-memory, encompassing how agents memorize, update, and retrieve long-term information-is under-evaluated due to the lack of benchmarks. We term agents with memory mechanisms as memory agents. In this paper, we identify four core competencies essential for memory agents: accurate retrieval, test-time learning, long-range understanding, and conflict resolution. Existing datasets either rely on limited context lengths or are tailored for static, long-context settings like book-based QA, which do not reflect the interactive, multi-turn nature of memory agents that incrementally accumulate information. Furthermore, no existing benchmarks cover all four competencies. Therefore, we introduce MemoryAgentBench, a new benchmark specifically designed for memory agents. Our benchmark combines reformulated existing datasets with newly constructed ones, covering the above four memory competencies, providing a systematic and challenging testbed for assessing memory quality. We evaluate a diverse set of memory agents, ranging from simple context-based and retrieval-augmented generation (RAG) systems to advanced agents with external memory modules and tool integration. Empirical results reveal that current methods fall short of mastering all four competencies, underscoring the need for further research into comprehensive memory mechanisms for LLM agents.

Hallucinations in multimodal large language models (MLLMs) -- where the model generates content inconsistent with the input image -- pose significant risks in real-world applications, from misinformation in visual question answering to unsafe errors in decision-making. Existing benchmarks primarily test recognition accuracy, i.e., evaluating whether models can select the correct answer among distractors. This overlooks an equally critical capability for trustworthy AI: recognizing when none of the provided options are correct, a behavior reflecting epistemic humility. We present HumbleBench, a new hallucination benchmark designed to evaluate MLLMs' ability to reject plausible but incorrect answers across three hallucination types: object, relation, and attribute. Built from a panoptic scene graph dataset, we leverage fine-grained scene graph annotations to extract ground-truth entities and relations, and prompt GPT-4-Turbo to generate multiple-choice questions, followed by a rigorous manual filtering process. Each question includes a "None of the above" option, requiring models not only to recognize correct visual information but also to identify when no provided answer is valid. We evaluate a variety of state-of-the-art MLLMs -- including both general-purpose and specialized reasoning models -- on HumbleBench and share valuable findings and insights with the community. By incorporating explicit false-option rejection, HumbleBench fills a key gap in current evaluation suites, providing a more realistic measure of MLLM reliability in safety-critical settings. Our code and dataset are released publicly and can be accessed at https://github.com/maifoundations/HumbleBench.

Recent advances in large reasoning language models (LRLMs) rely on test-time scaling, which extends long chain-of-thought (CoT) generation to solve complex tasks. However, overthinking in long CoT not only slows down the efficiency of problem solving, but also risks accuracy loss due to the extremely detailed or redundant reasoning steps. We propose a simple yet effective method that allows LLMs to self-truncate CoT sequences by early exit during generation. Instead of relying on fixed heuristics, the proposed method monitors model behavior at potential reasoning transition points (e.g.,"Wait" tokens) and dynamically terminates the next reasoning chain's generation when the model exhibits high confidence in a trial answer. Our method requires no additional training and can be seamlessly integrated into existing o1-like reasoning LLMs. Experiments on 10 reasoning benchmarks (e.g., GSM8K, MATH-500, AMC, GPQA, AIME and LiveCodeBench) show that the proposed method is consistently effective on 11 cutting-edge reasoning LLMs of varying series and sizes, reducing the length of CoT sequences by an average of 19.1% to 80.1% while improving accuracy by 0.3% to 5.0%.

Recent advancements in large language models (LLMs) have demonstrated significant progress in math and code reasoning capabilities. However, existing code benchmark are limited in their ability to evaluate the full spectrum of these capabilities, particularly at the competitive level. To bridge this gap, we introduce OJBench, a novel and challenging benchmark designed to assess the competitive-level code reasoning abilities of LLMs. OJBench comprises 232 programming competition problems from NOI and ICPC, providing a more rigorous test of models' reasoning skills. We conducted a comprehensive evaluation using OJBench on 37 models, including both closed-source and open-source models, reasoning-oriented and non-reasoning-oriented models. Our results indicate that even state-of-the-art reasoning-oriented models, such as o4-mini and Gemini-2.5-pro-exp, struggle with highly challenging competition-level problems. This highlights the significant challenges that models face in competitive-level code reasoning.

Large vision-language models have recently demonstrated impressive performance in planning and control tasks, driving interest in their application to real-world robotics. However, deploying these models for reasoning in embodied contexts is limited by their ability to incorporate long-term experience collected across multiple days and represented by vast collections of images. Current VLMs typically struggle to process more than a few hundred images concurrently, highlighting the need for more efficient mechanisms to handle long-term memory in embodied settings. To effectively evaluate these models for long-horizon control, a benchmark must specifically target scenarios where memory is crucial for success. Existing long-video QA benchmarks overlook embodied challenges like object manipulation and navigation, which demand low-level skills and fine-grained reasoning over past interactions. Moreover, effective memory integration in embodied agents involves both recalling relevant historical information and executing actions based on that information, making it essential to study these aspects together rather than in isolation. In this work, we introduce a new benchmark for long-range embodied tasks in the Habitat simulator. This benchmark evaluates memory-based capabilities across 60 tasks requiring sustained engagement and contextual awareness in an environment. The tasks can also be procedurally extended to longer and more challenging versions, enabling scalable evaluation of memory and reasoning. We also present baselines that integrate state-of-the-art VLMs with low level navigation policies, assessing their performance on these memory-intensive tasks and highlight areas for improvement.

Reinforcement learning from verifiable rewards has emerged as a powerful technique for enhancing the complex reasoning abilities of Large Language Models (LLMs). However, these methods are fundamentally constrained by the ''learning cliff'' phenomenon: when faced with problems far beyond their current capabilities, models consistently fail, yielding a persistent zero-reward signal. In policy optimization algorithms like GRPO, this collapses the advantage calculation to zero, rendering these difficult problems invisible to the learning gradient and stalling progress. To overcome this, we introduce Scaf-GRPO (Scaffolded Group Relative Policy Optimization), a progressive training framework that strategically provides minimal guidance only when a model's independent learning has plateaued. The framework first diagnoses learning stagnation and then intervenes by injecting tiered in-prompt hints, ranging from abstract concepts to concrete steps, enabling the model to construct a valid solution by itself. Extensive experiments on challenging mathematics benchmarks demonstrate Scaf-GRPO's effectiveness, boosting the pass@1 score of the Qwen2.5-Math-7B model on the AIME24 benchmark by a relative 44.3% over a vanilla GRPO baseline. This result demonstrates our framework provides a robust and effective methodology for unlocking a model's ability to solve problems previously beyond its reach, a critical step towards extending the frontier of autonomous reasoning in LLM.

Recent advances in large language models (LLMs) have increased the demand for comprehensive benchmarks to evaluate their capabilities as human-like agents. Existing benchmarks, while useful, often focus on specific application scenarios, emphasizing task completion but failing to dissect the underlying skills that drive these outcomes. This lack of granularity makes it difficult to deeply discern where failures stem from. Additionally, setting up these environments requires considerable effort, and issues of unreliability and reproducibility sometimes arise, especially in interactive tasks. To address these limitations, we introduce the Massive Multitask Agent Understanding (MMAU) benchmark, featuring comprehensive offline tasks that eliminate the need for complex environment setups. It evaluates models across five domains, including teal{Tool-use}, teal{Directed Acyclic Graph (DAG) QA}, teal{Data Science and Machine Learning coding}, teal{Contest-level programming} and teal{Mathematics}, and covers five essential capabilities: orange{Understanding}, orange{Reasoning}, orange{Planning}, orange{Problem-solving}, and orange{Self-correction}. With a total of 20 meticulously designed tasks encompassing over 3K distinct prompts, MMAU provides a comprehensive framework for evaluating the strengths and limitations of LLM agents. By testing 18 representative models on MMAU, we provide deep and insightful analyses. Ultimately, MMAU not only sheds light on the capabilities and limitations of LLM agents but also enhances the interpretability of their performance. Datasets and evaluation scripts of MMAU are released at https://github.com/apple/axlearn/docs/research/mmau.

Large Language Models (LLMs) have demonstrated impressive capabilities in natural language processing tasks, such as text generation and semantic understanding. However, their performance on numerical reasoning tasks, such as basic arithmetic, numerical retrieval, and magnitude comparison, remains surprisingly poor. This gap arises from their reliance on surface-level statistical patterns rather than understanding numbers as continuous magnitudes. Existing benchmarks primarily focus on either linguistic competence or structured mathematical problem-solving, neglecting fundamental numerical reasoning required in real-world scenarios. To bridge this gap, we propose NumericBench, a comprehensive benchmark to evaluate six fundamental numerical capabilities: number recognition, arithmetic operations, contextual retrieval, comparison, summary, and logical reasoning. NumericBench includes datasets ranging from synthetic number lists to the crawled real-world data, addressing challenges like long contexts, noise, and multi-step reasoning. Extensive experiments on state-of-the-art LLMs, including GPT-4 and DeepSeek, reveal persistent weaknesses in numerical reasoning, highlighting the urgent need to improve numerically-aware language modeling. The benchmark is released in: https://github.com/TreeAI-Lab/NumericBench.

We introduce DABstep, a novel benchmark for evaluating AI agents on realistic multi-step data analysis tasks. DABstep comprises over 450 real-world challenges derived from a financial analytics platform, requiring models to combine code-based data processing with contextual reasoning over heterogeneous documentation. Each task demands an iterative, multi-step problem-solving approach, testing capabilities in data manipulation, cross-referencing multiple sources, and precise result reporting. The benchmark provides a factoid-style answer format with automatic correctness checks for objective scoring at scale. We evaluate leading LLM-based agents, revealing a substantial performance gap: even the best agent achieves only 14.55% accuracy on the hardest tasks. We detail our benchmark's design, dataset composition, task formulation, evaluation protocol, report baseline results and analyze failure modes. DABstep is released with a public leaderboard and toolkit to accelerate research in autonomous data analysis.

We study building embodied agents for open-ended creative tasks. While existing methods build instruction-following agents that can perform diverse open-ended tasks, none of them demonstrates creativity -- the ability to give novel and diverse task solutions implicit in the language instructions. This limitation comes from their inability to convert abstract language instructions into concrete task goals in the environment and perform long-horizon planning for such complicated goals. Given the observation that humans perform creative tasks with the help of imagination, we propose a class of solutions for creative agents, where the controller is enhanced with an imaginator that generates detailed imaginations of task outcomes conditioned on language instructions. We introduce several approaches to implementing the components of creative agents. We implement the imaginator with either a large language model for textual imagination or a diffusion model for visual imagination. The controller can either be a behavior-cloning policy learned from data or a pre-trained foundation model generating executable codes in the environment. We benchmark creative tasks with the challenging open-world game Minecraft, where the agents are asked to create diverse buildings given free-form language instructions. In addition, we propose novel evaluation metrics for open-ended creative tasks utilizing GPT-4V, which holds many advantages over existing metrics. We perform a detailed experimental analysis of creative agents, showing that creative agents are the first AI agents accomplishing diverse building creation in the survival mode of Minecraft. Our benchmark and models are open-source for future research on creative agents (https://github.com/PKU-RL/Creative-Agents).

Ensuring safe and effective use of AI requires understanding and anticipating its performance on novel tasks, from advanced scientific challenges to transformed workplace activities. So far, benchmarking has guided progress in AI, but it has offered limited explanatory and predictive power for general-purpose AI systems, given the low transferability across diverse tasks. In this paper, we introduce general scales for AI evaluation that can explain what common AI benchmarks really measure, extract ability profiles of AI systems, and predict their performance for new task instances, in- and out-of-distribution. Our fully-automated methodology builds on 18 newly-crafted rubrics that place instance demands on general scales that do not saturate. Illustrated for 15 large language models and 63 tasks, high explanatory power is unleashed from inspecting the demand and ability profiles, bringing insights on the sensitivity and specificity exhibited by different benchmarks, and how knowledge, metacognition and reasoning are affected by model size, chain-of-thought and distillation. Surprisingly, high predictive power at the instance level becomes possible using these demand levels, providing superior estimates over black-box baseline predictors based on embeddings or finetuning, especially in out-of-distribution settings (new tasks and new benchmarks). The scales, rubrics, battery, techniques and results presented here represent a major step for AI evaluation, underpinning the reliable deployment of AI in the years ahead. (Collaborative platform: https://kinds-of-intelligence-cfi.github.io/ADELE.)

The paper proposes a novel machine learning-based approach to the pathfinding problem on extremely large graphs. This method leverages diffusion distance estimation via a neural network and uses beam search for pathfinding. We demonstrate its efficiency by finding solutions for 4x4x4 and 5x5x5 Rubik's cubes with unprecedentedly short solution lengths, outperforming all available solvers and introducing the first machine learning solver beyond the 3x3x3 case. In particular, it surpasses every single case of the combined best results in the Kaggle Santa 2023 challenge, which involved over 1,000 teams. For the 3x3x3 Rubik's cube, our approach achieves an optimality rate exceeding 98%, matching the performance of task-specific solvers and significantly outperforming prior solutions such as DeepCubeA (60.3%) and EfficientCube (69.6%). Additionally, our solution is more than 26 times faster in solving 3x3x3 Rubik's cubes while requiring up to 18.5 times less model training time than the most efficient state-of-the-art competitor.

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development, commercial investment, and scientific discovery, unfold in long-horizon and partially observable scenarios where success hinges on sustained reasoning, planning, memory management, and tool use. Existing benchmarks rarely capture these long-horizon challenges, leaving a gap in systematic evaluation. To bridge this gap, we introduce UltraHorizon a novel benchmark that measures the foundational capabilities essential for complex real-world challenges. We use exploration as a unifying task across three distinct environments to validate these core competencies. Agents are designed in long-horizon discovery tasks where they must iteratively uncover hidden rules through sustained reasoning, planning, memory and tools management, and interaction with environments. Under the heaviest scale setting, trajectories average 200k+ tokens and 400+ tool calls, whereas in standard configurations they still exceed 35k tokens and involve more than 60 tool calls on average. Our extensive experiments reveal that LLM-agents consistently underperform in these settings, whereas human participants achieve higher scores, underscoring a persistent gap in agents' long-horizon abilities. We also observe that simple scaling fails in our task. To better illustrate the failure of agents, we conduct an in-depth analysis of collected trajectories. We identify eight types of errors and attribute them to two primary causes: in-context locking and functional fundamental capability gaps. https://github.com/StarDewXXX/UltraHorizon{Our code will be available here.}

Existing tasks fall short in evaluating reasoning ability of Large Language Models (LLMs) in an interactive, unknown environment. This deficiency leads to the isolated assessment of deductive, inductive, and abductive reasoning, neglecting the integrated reasoning process that is indispensable for humans discovery of real world. We introduce a novel evaluation paradigm, black-box interaction, to tackle this challenge. A black-box is defined by a hidden function that maps a specific set of inputs to outputs. LLMs are required to unravel the hidden function behind the black-box by interacting with it in given exploration turns, and reasoning over observed input-output pairs. Leveraging this idea, we build the Oracle benchmark which comprises 6 types of black-box task and 96 black-boxes. 19 modern LLMs are benchmarked. o3 ranks first in 5 of the 6 tasks, achieving over 70\% accuracy on most easy black-boxes. But it still struggles with some hard black-box tasks, where its average performance drops below 40\%. Further analysis indicates a universal difficulty among LLMs: They lack the high-level planning capability to develop efficient and adaptive exploration strategies for hypothesis refinement.

While Large Language Models (LLMs) demonstrate impressive performance in mathematics, existing math benchmarks come with significant limitations. Many focus on problems with fixed ground-truth answers, and are often saturated due to problem simplicity or the viability of guessing or memorization. Crucially, they capture only a narrow subset of relevant math problems. To address this research gap, we introduce \mc, a new benchmark of 126 challenging problems sourced from various math competitions, which targets constructive proofs, a widely encountered problem type requiring the construction of mathematical objects with specific properties. These proofs are particularly suitable for LLM evaluation, as solution correctness can be easily verified. Our automated verifiers also enable MathConstruct to generate problem variations, used to evaluate robustness. State-of-the-art LLMs solve only 54% of MathConstruct problems, highlighting its complexity and importance for LLM evaluation.