The Thinking Leakage in Reinforcement Learning for LLMs

2026-10-16来源 Hacker News NewEnglish

Article URL: https://arxiv.org/abs/2610.14270

Comments URL: https://news.ycombinator.com/item?id=50113842

Points: 2

# Comments: 0

原文：https://www.a8q9.cn/en/article/the-thinking-leakage-in-reinforcement-learning-for-llms-39dba5.html

相关文章