tracked author

Yuxiao Dong

SAO and CompactionRL coauthor and Tsinghua computer science associate professor. His official homepage lists Zhenyu Hou and Yujiang Li as PhD students, records prior research roles at Meta AI and Microsoft Research Redmond, and directly links the @ericdongyx X account; the Tsinghua KEG X profile independently names the same handle.

2 archived notes X: high Homepage X

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