The Thinking Leakage in Reinforcement Learning for LLMs
arXiv:2610.14270v1 Announce Type: new Abstract: Hybrid reasoning models such as the Qwen3 series switch between a THINK mode and a NO-THINK mode through a few chat-template tokens. A popular recipe trains such models with reinforcement learning in NO-THINK mode and reports improved reasoning perfor…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-14 04:00 · arXiv cs.CL
The Thinking Leakage in Reinforcement Learning for LLMs