Bowen Zhou | Chlience Paper Archive

Bowen Zhou

Entropy Mechanism corresponding author and Self-Improving Agents survey corresponding author. TsinghuaC3I page identifies him as Tsinghua Department of Electronics permanent professor, Huiyan Chair Professor, IEEE Fellow and CAAI Fellow; Google Scholar identifies him as Director of Shanghai AI Lab and Chair Professor at Tsinghua.

2 archived notes X: not-found Homepage

Jun 28, 2026

Self Improving Agents in the Era of Experience: A Survey of Self to Meta Evolution

这篇 survey 把 self improving agents 从模型自我训练扩展为部署后 runtime system 的 trace to capability 问题：harness 将交互 trace 编译成可验证 experience，再分别写入 skills、memory、environment/tool boundary、model parameters 或 meta layer。它的主要贡献是给 self impro...

2026-06-25-self-improving-agents-era-experience-survey Agent RL Agent Memory Agent Workflow

Jun 21, 2026

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

这篇论文把 reasoning LLM 的 RLVR 训练瓶颈重新表述为 policy entropy 的消耗过程：在没有 entropy / KL 干预时，reward 提升和 entropy 下降之间可以被经验式 $R= a\exp(\mathcal H)+b$ 拟合；进一步用 softmax policy 的 entropy dynamics 说明，高概率且高 advantage 的 token update 会持续降低 ent...

2505.22617-entropy-mechanism-rl-reasoning-language-models Training Stability Reasoning RL RL Theory

Related Notes

Self Improving Agents in the Era of Experience: A Survey of Self to Meta Evolution

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models