AI RESEARCH
Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning
arXiv CS.LG
•
ArXi:2606.02020v1 Announce Type: cross This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of exploration transitioning sharply to a Confidence Region of convergence. We nstrate that the Confidence Region possesses two critical properties: 1) High Reliability -- answers in the confidence region become highly accurate and stable, and 2) High Redundancy -- models generate unnecessary tokens long after reaching the correct answer.