@article{whataresteplevelrewardmodelsrewarding,
  title = {What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning},
  author = {Yiran Ma and Zui Chen and Tianqiao Liu and Mi Tian and Zhuo Liu and Zitao Liu and Weiqi Luo},
  year = {2024},
  eprint = {2412.15904},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.15904v2},
}