%0 Journal Article %1 journals/corr/abs-2310-10080 %A Ma, Qianli %A Zhou, Haotian %A Liu, Tingkai %A Yuan, Jianbo %A Liu, Pengfei %A You, Yang %A Yang, Hongxia %D 2023 %J CoRR %K dblp %T Let's reward step by step: Step-Level reward model as the Navigators for Reasoning. %U http://dblp.uni-trier.de/db/journals/corr/corr2310.html#abs-2310-10080 %V abs/2310.10080

@article{journals/corr/abs-2310-10080, added-at = {2023-10-25T00:00:00.000+0200}, author = {Ma, Qianli and Zhou, Haotian and Liu, Tingkai and Yuan, Jianbo and Liu, Pengfei and You, Yang and Yang, Hongxia}, biburl = {https://www.bibsonomy.org/bibtex/24c6a3d3fb39dc824335862df081165c1/dblp}, ee = {https://doi.org/10.48550/arXiv.2310.10080}, interhash = {6c3657069de2ef6a2294cbac2fc19096}, intrahash = {4c6a3d3fb39dc824335862df081165c1}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-09T00:27:48.000+0200}, title = {Let's reward step by step: Step-Level reward model as the Navigators for Reasoning.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2310.html#abs-2310-10080}, volume = {abs/2310.10080}, year = 2023 }