Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs 事件

Hidden Thoughts Are Not Secret: Reasoning Trace Exposure in LLMs arXiv:2606.00642v1 Announce Type: new Abstract: Reasoning traces have become a valuable form of learning signals for improving and transferring the capabilities of large language models. In particular, detailed traces can help distill reasoning behavior from stronger teacher models into weaker student models. The value of capability transfer has motivated many deployed systems with reasoning models to hide raw internal traces and