@article{letsrewardstepbystepsteplevelreward, title = {Let's reward step by step: Step-Level reward model as the Navigators for Reasoning}, author = {Qianli Ma and Haotian Zhou and Tingkai Liu and Jianbo Yuan and PengFei Liu and Yang You and Hongxia Yang}, year = {2023}, eprint = {2310.10080}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2310.10080v1}, }