tracked author

Zhenyu Hou

SAO and CompactionRL co-first author and Tsinghua computer science PhD student advised by Yuxiao Dong and Jie Tang. His homepage records work on language-model post-training, agents, reinforcement learning, and the GLM-4.5 / GLM-5 series; both papers connect this work to his Z.AI internship.

2 archived notes X: not-found Homepage GitHub

Related Notes

按论文归档时间排序，展示该作者在本站已经出现的材料。

归档 Jul 13, 2026

CompactionRL: Reinforcement Learning with Context Compaction for Long Horizon Agents

CompactionRL 用独立 critic 和按后续 token 数折扣的跨段优势训练上下文压缩轨迹；两个模型在启用压缩的 coding 评测中提高 Pass@1，但 SUPO 已覆盖摘要—执行联合训练与全 token 归一化，且论文未报告直接对照或总计算。

待审阅 2607.05378-compactionrl-context-compaction-agent-rl Agent Memory Agent RL Credit Assignment

归档 Jul 11, 2026

Single Rollout Asynchronous Optimization for Agentic Reinforcement Learning

用每 prompt 单 rollout、强化 critic 与双侧 token mask 替代异步 GRPO 的组内等待和 group baseline。

待审阅 2607.07508-sao-single-rollout-asynchronous-agentic-rl RL Algorithm Agent RL Credit Assignment