AI RESEARCH
Decoding the Critique Mechanism in Large Reasoning Models
arXiv CS.LG
•
ArXi:2603.16331v1 Announce Type: new Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions, yielding strong performance on complex logical benchmarks. We hypothesize that such behaviors are beneficial only when the model has sufficiently strong "critique" ability to detect its own mistakes. This work systematically investigates how current LRMs recover from errors by inserting arithmetic mistakes in their intermediate reasoning steps.