arXiv 2610.16794 · cs.LG · 2026-10-12
TPPO: Tracking-Value PPO For Language Model Reasoning
Futing Wang, Chenxi Li, Jianhao Yan, Yun Luo, Zhi Wang, Yizhuo Li, Runzhe Zhan, Yu Cheng 等 9 人
机构待核实
在最新榜 #151 本站收录于 2026-10-21
一句话要点
TPPO 用累加式价值参数化追踪推理过程中的价值变化，改进 PPO 的逐 token 信用分配。
TPPO uses a cumulative value parameterisation to track value along the trajectory, improving token-level credit in PPO for reasoning.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
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。