5 papers
Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization
Yihang Yao, Zhepeng Cen, Haohong Lin +6
Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following a…
Behavior Injection: Preparing Language Models for Reinforcement Learning
Zhepeng Cen, Yihang Yao, William Han +2
Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very i…
MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning
Yiqing Liang, Jielin Qiu, Wenhao Ding +7
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art perform…
Your Language Model May Think Too Rigidly: Achieving Reasoning Consistency with Symmetry-Enhanced Training
Yihang Yao, Zhepeng Cen, Miao Li +6
Large Language Models (LLMs) have demonstrated strong reasoning capabilities across various tasks. However, even minor variations in query phrasing, despite preserving the underlyi…
Reinforcement Learning in a Safety-Embedded MDP with Trajectory Optimization
Fan Yang, Wenxuan Zhou, Zuxin Liu +2
Safe Reinforcement Learning (RL) plays an important role in applying RL algorithms to safety-critical real-world applications, addressing the trade-off between maximizing rewards a…