新闻
CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- CRoS method improves language model reasoning by rewarding chain-of-thought steps based on scrambled order rather than deletion, achieving 46.8% accuracy on unseen logic tasks.
- 为何重要
- Matters for engineers training reasoning models with reinforcement learning who want better out-of-domain generalization and more faithful intermediate reasoning steps.
- 注意
- Method tested only on Gemma-3-4B model; unclear how well scrambling-based causality transfers to larger models or different reasoning domains beyond logic and games.
- language model
- reasoning
- reinforcement learning
- rlvr
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。