19 papers
WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training
Zehao Chen, Gongxun Li, Tianxiang Ai +9
On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline distillation. The sa…
Counterfactual Credit Policy Optimization for Multi-Agent Collaboration
Zhongyi Li, Wan Tian, Jinju Chen +4
Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assi…
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger
Zehao Chen, Gongxun Li, Tianxiang Ai +9
As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training…
Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
Xiaodong Lu, Xiaohan Wang, Jiajun Chai +7
Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods uti…
Heterogeneous Agent Collaborative Reinforcement Learning
Zhixia Zhang, Zixuan Huang, Gongxun Li +10
We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new Reinforcement Learning from Verifiable Reward (RLVR) problem that addresses the inefficiencies…
Does Your Reasoning Model Implicitly Know When to Stop Thinking?
Zixuan Huang, Xin Xia, Yuxi Ren +11
Recent advancements in large reasoning models (LRMs) have greatly improved their capabilities on complex reasoning tasks through Long Chains of Thought (CoTs). However, this approa…