理解推理模型的思维过程：基于舍恩菲尔德片段理论的视角

摘要

尽管大型推理模型（LRMs）能够生成广泛的思维链推理，我们仍缺乏一个系统性的框架来理解这些思维的结构。本文提出了一种新颖方法，通过应用Schoenfeld的认知框架——人类数学问题解决的经典理论，来分析LRMs的推理轨迹。我们对模型生成的数学问题解决方案中的数千个句子和段落进行了标注，使用了七种认知标签（如计划、实施、验证）。这一成果首次公开了用于机器推理细粒度分析的基准，包括大规模标注语料库和详细的标注指南。我们的初步分析揭示了LRM推理中的独特模式，例如认知状态间的转换动态。该框架为解释LRM认知提供了理论依据，并为未来开发更具可控性和透明性的推理系统奠定了基础。

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.

理解推理模型的思维过程：基于舍恩菲尔德片段理论的视角

Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld's Episode Theory

摘要

Support