Diego Klabjan

Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide

This work theoretically shows that directly leveraging PRM score is vulnerable to verifier noise through an extreme-value effect: non-viable prefixes become more likely to receive spuriously high scores as reasoning depth increase, leading to a training-free robust process supervision method that preserves promising alternatives when step-level scores are noisy.