9 papers
Group Entropy-Controlled Policy Optimization
Guangran Cheng, Chengqi Lyu, Songyang Gao +2
Entropy control has become an effective tool in reinforcement learning (RL) of large language models (LLMs), helping balance exploration-exploitation trade-off during alignment pro…
Libra: Efficient Resource Management for Agentic RL Post-Training
Kaiwen Chen, Xin Tan, Jingzong Li +6
Reinforcement learning (RL) has emerged as a standard post-training paradigm for shaping large language models (LLMs) into capable agents. In agentic RL, the rollout stage generate…
ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
Ziyan Liu, Xueda Shen, Yuzhe Gu +7
Large Reasoning Models (LRMs) have achieved remarkable progress thanks to Reinforcement Learning with Verifiable Rewards (RLVR) on Chain-of-Thoughts (CoTs). However, since long CoT…
OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification
Zijian Wu, Lingkai Kong, Wenwei Zhang +12
Large language models (LLMs) have achieved significant progress in solving complex reasoning tasks by Reinforcement Learning with Verifiable Rewards (RLVR). This advancement is als…
Intern-S1-MO: Long-horizon Reasoning Agent for Olympiad?Level Mathematical Problem Solving
Yuzhe Gu, Songyang Gao, Zijian Wu +18
Large Reasoning Models (LRMs) have expanded the mathematical reasoning frontier through Chain-of-Thought (CoT) techniques and Reinforcement Learning with Verifiable Rewards (RLVR),…
Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
Haiteng Zhao, Junhao Shen, Yiming Zhang +7
Large language model (LLM) agents exhibit strong mathematical problem-solving abilities and can even solve International Mathematical Olympiad (IMO) level problems with the assista…
CODA: Coordinating the Cerebrum and Cerebellum for a Dual-Brain Computer Use Agent with Decoupled Reinforcement Learning
Zeyi Sun, Yuhang Cao, Jianze Liang +8
Autonomous agents for Graphical User Interfaces (GUIs) face significant challenges in specialized domains such as scientific computing, where both long-horizon planning and precise…
Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning
Junhao Shen, Haiteng Zhao, Yuzhe Gu +7
Enhancing large vision-language models (LVLMs) with visual slow-thinking reasoning is crucial for solving complex multimodal tasks. However, since LVLMs are mainly trained with vis…
The Imitation Game: Turing Machine Imitator is Length Generalizable Reasoner
Zhouqi Hua, Wenwei Zhang, Chengqi Lyu +5
Length generalization, the ability to solve problems of longer sequences than those observed during training, poses a core challenge of Transformer-based large language models (LLM…