arXiv 2610.01509 · cs.AI · 2026-10-01
Sharpening Tax in Post-Training
Changdae Oh, Qi Zeng, Qi Qi, Andrey Zhmoginov, Deren Lei, Yun He, Hoang Phan, Hangoo Kang 等 10 人
Meta
在最新榜 #86 本站收录于 2026-10-21
一句话要点
发现 RL 后训练在 Agent 任务上有“锐化税”：预训练模型配轻量框架，多次尝试的覆盖率反而更高。
Finds a 'sharpening tax': pre-trained LLMs with a light harness often beat post-trained ones on agentic coverage despite lower pass@1.
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
- RULER: Instance-aware Rubric Rewards for SVG Generation ▲104
- TPPO: Tracking-Value PPO For Language Model Reasoning ▲96
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。