Saved in:
Bibliographic Details
Main Authors: Li, Ming, Zhang, Nan, Fan, Chenrui, Jiao, Hong, Fu, Yanbin, Peters, Sydney, Xu, Qingshu, Lissitz, Robert, Zhou, Tianyi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.14662
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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.