view article Article Announcing LiteCoder-Terminal: Lightweight Terminal Agents with <1k Synthesized Trajectories 12 days ago • 9
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking Paper • 2502.20730 • Published Feb 28 • 38
Aligning Large Language Models via Self-Steering Optimization Paper • 2410.17131 • Published Oct 22, 2024 • 24
ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers Paper • 2504.00502 • Published Apr 1 • 26
RefCritic: Training Long Chain-of-Thought Critic Models with Refinement Feedback Paper • 2507.15024 • Published Jul 20 • 14
Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window Paper • 2510.08276 • Published Oct 9 • 9