arXiv 2610.23181 · cs.LG · 2026-10-16
Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning
Heming Zou, Qi Wang, Yixiu Mao, Yun Qu, Yuyi Guo, Zeyuan Liu, Chenglin Li, Weijie Liu 等 10 人
Tencent Hunyuan
在最新榜 #284 本站收录于 2026-10-22
一句话要点
TreeOPSD 把多轮交互建成树，回传终局奖励得到每轮的隐式信用，再做无评论家的自蒸馏，用于长程智能体强化学习。
TreeOPSD builds a tree over agent turns, backs up terminal rewards into turn-level credit and self-distills without a critic for long-horizon agent RL.
阅读 arXiv 原文 PDF Hugging Face 讨论
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。