Skip to content

What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning.

Yiran Ma, Zui Chen, Tianqiao Liu, Mi Tian, Zhuo Liu, Zitao Liu, Weiqi Luo

VenueA*AAAI
Year2025
ProceedingsAAAI

Browse the full AAAI paper archive.