Haitao Mi

haitaominlp's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 6 papers 9 days ago

VeriGUI: Verifiable Long-Chain GUI Dataset

Paper • 2508.04026 • Published Aug 6 • 156

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

Paper • 2508.01191 • Published Aug 2 • 234

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published 19 days ago • 117

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

Paper • 2508.13167 • Published Aug 6 • 123

Mobile-Agent-v3: Foundamental Agents for GUI Automation

Paper • 2508.15144 • Published 17 days ago • 58

Self-Rewarding Vision-Language Model via Reasoning Decomposition

Paper • 2508.19652 • Published 11 days ago • 79

upvoted a paper 29 days ago

R-Zero: Self-Evolving Reasoning LLM from Zero Data

Paper • 2508.05004 • Published Aug 7 • 123

upvoted a paper about 1 month ago

Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training

Paper • 2508.00414 • Published Aug 1 • 89

upvoted 3 papers about 2 months ago

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

Paper • 2507.10532 • Published Jul 14 • 88

One Token to Fool LLM-as-a-Judge

Paper • 2507.08794 • Published Jul 11 • 31

Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving

Paper • 2507.06804 • Published Jul 7 • 15

upvoted 2 papers 4 months ago

Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity

Paper • 2505.11107 • Published May 16 • 29

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation

Paper • 2505.10962 • Published May 16 • 8

upvoted 3 papers 5 months ago

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Paper • 2504.13837 • Published Apr 18 • 134

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Paper • 2504.11456 • Published Apr 15 • 13

Expanding RL with Verifiable Rewards Across Diverse Domains

Paper • 2503.23829 • Published Mar 31 • 24

upvoted 3 papers 11 months ago

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning

Paper • 2410.06508 • Published Oct 9, 2024 • 11

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

Paper • 2410.03864 • Published Oct 4, 2024 • 12

HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows

Paper • 2409.17433 • Published Sep 25, 2024 • 9