tracked author

Yi Jing

CompactionRL coauthor and Tsinghua undergraduate in Xinya College and computer science. Her homepage records current THUKEG and PKUICL internships and research in interpretability, post-training, and AI for research; CompactionRL was completed while she interned at Z.AI.

1 archived notes X: not-found HomepageGitHubHugging Face

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

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 MemoryAgent RLCredit Assignment