Author

Ze-Yu Chen

h-index 0 View on Semantic Scholar

We have 3 of 6 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning

Asynchronous reinforcement learning (RL) accelerates large language model (LLM) post-training by overlapping rollout generation with policy optimization, but the resulting stale, off-policy data can destabilize optimization and ultimately cause policy collapse. Existing methods typically retain or discard tokens based...

Guan-Qun Zhao, Zi-Jun Xie, Binbin Zheng et al. · arXiv.org · 2 citations

#artificial intelligence Preprint Sep 2026

BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL

Asynchronous reinforcement learning has become the standard way to scale training for large language models (LLM), but the resulting policy lag biases the critic toward the stale behavior policy. Existing work on asynchronous LLM training corrects the actor and leaves this bias unaddressed, while the off-policy value c...

Guan-Qun Zhao, Zi-Jun Xie, Binbin Zheng et al. · 0 citations

Jul 2026

Group-Reflective Self-Distillation for Agentic Reinforcement Learning

Group-Reflective Self-Distillation (GRSD), which derives capability-aligned and outcome-discriminative guidance from the policy's own verified rollouts, and refines turn-level credit assignment by modulating outcome-based advantages while preserving the verifier-determined learning direction.

Binbin Zheng, Zi-Jun Xie, Guan-Qun Zhao et al. · arXiv.org · 1 citation