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 and 2 more
Meta
In latest · #86 Added on 2026-10-21
One-line takeaway
Finds a 'sharpening tax': pre-trained LLMs with a light harness often beat post-trained ones on agentic coverage despite lower pass@1.
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。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Reinforcement learning
- 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
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-22.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.