5 papers
BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL
Guanqun Zhao, Zijun Xie, Binbin Zheng +3
Asynchronous reinforcement learning has become the standard way to scale training for language models, but the resulting policy lag biases the critic toward the stale behavior poli…
Group-Reflective Self-Distillation for Agentic Reinforcement Learning
Binbin Zheng, Zijun Xie, Guanqun Zhao +4
Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervis…
Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning
Guanqun Zhao, Zijun Xie, Binbin Zheng +5
Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, o…
ACPO: Asymmetric Credit Policy Optimization via Mode-Local Entropy Surrogate
Zijun Xie, Yuyang You, Yongzhi Li +8
Outcome-supervised reinforcement learning scales to verifiable reasoning tasks, but trajectory-level rewards assign the same outcome signal to all sampled tokens, overlooking their…
ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL
Zijun Xie, Binbin Zheng, Enlei Gong +7
Long-horizon language agents must repeatedly interact with tools, accumulate evidence, and make decisions under bounded context windows. Context-management methods make such rollou…