理解推理模型的思考過程：從Schoenfeld的片段理論視角出發

摘要

儘管大型推理模型（LRMs）能夠生成廣泛的思維鏈推理，我們仍缺乏一個系統性的框架來理解這些思維的結構。在本論文中，我們引入了一種新穎的方法，即應用Schoenfeld的「解題片段理論」——一個經典的人類數學問題解決認知框架——來分析LRMs的推理軌跡。我們使用七種認知標籤（例如，計劃、實施、驗證）對模型生成的數學問題解決方案中的數千個句子和段落進行了註釋。其結果是首個公開可用的機器推理細粒度分析基準，包括一個大型註釋語料庫和詳細的註釋指南。我們的初步分析揭示了LRM推理中的獨特模式，例如認知狀態之間的轉換動態。這一框架為解釋LRM認知提供了理論基礎的方法論，並為未來開發更具可控性和透明性的推理系統奠定了基礎。

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.

理解推理模型的思考過程：從Schoenfeld的片段理論視角出發

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

摘要

Support