arXiv 2610.22174 · cs.CL · 2026-10-15
Mosaic: Multi-Session Agentic Reinforcement Learning
Yilong Xu, Minrui Xu, Xinyu Zhou, Xiang Long, Haochen Tan, Zhijiang Guo
LARK Lab@HKUST (GZ)
在最新榜 #207 本站收录于 2026-10-21
一句话要点
Mosaic 把智能体强化学习扩展到多会话轨迹，匹配上下文压缩和子智能体分叉等真实推理方式。
Mosaic generalises agentic RL to multi-session trajectories, matching inference-time context compaction and sub-agent forking.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：强化学习
- Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation ▲218
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight ▲189
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches ▲152
- Sharpening Tax in Post-Training ▲111
- RULER: Instance-aware Rubric Rewards for SVG Generation ▲104
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。