AI RESEARCH
On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective
arXiv CS.LG
•
ArXi:2605.21260v1 Announce Type: new We develop a learning-theoretic framework for understanding Chain of Thought (CoT). We model CoT as the interaction between an answer map and a chain rule that generates intermediate questions autoregressively, and define the reasoning risk of a hypothesis under this interaction.