用人类解题理论分析大模型推理过程，揭示思维阶段转换规律。
Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory
- 引入认知心理学的解题阶段理论，标注模型推理中的思维状态。
- 构建首个公开的大模型推理细粒度分析基准，含数千条标注数据。
- 适用于研究模型可解释性、提升推理可控性的研究人员。
尽管大型推理模型（LRMs）生成了大量思维链式推理，但我们缺乏理解这些思维结构的系统性框架。本文首次将经典的霍恩费尔德解题阶段理论（Schoenfeld's Episode Theory）应用于分析LRM的推理轨迹。通过使用七种认知标签（如计划、执行、验证）对数千句模型生成的数学问题解答进行标注，构建了首个公开可用的细粒度机器推理分析基准，包含大规模标注语料库和详尽的标注手册。初步分析揭示了LRM推理中认知状态间的转换动态等显著模式。该框架为解释模型认知提供了理论基础，推动未来更可控、透明的推理系统发展。
原文摘要 · Abstract (English)
While Large Reasoning Models (LRMs) generate extensive chain-of-thought reasoning, we lack a principled framework for understanding how these thoughts are structured. In this paper, we introduce a novel approach by applying Schoenfeld's Episode Theory, a classic cognitive framework for human mathematical problem-solving, to analyze the reasoning traces of LRMs. We annotated thousands of sentences and paragraphs from model-generated solutions to math problems using seven cognitive labels (e.g., Plan, Implement, Verify). The result is the first publicly available benchmark for the fine-grained analysis of machine reasoning, including a large annotated corpus and detailed annotation guidebooks. Our preliminary analysis reveals distinct patterns in LRM reasoning, such as the transition dynamics between cognitive states. This framework provides a theoretically grounded methodology for interpreting LRM cognition and enables future work on more controllable and transparent reasoning systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。