@article{pspoaneffectiveprocesssupervisedpolicy, title = {PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment}, author = {Jiawei Li and Xinyue Liang and Junlong Zhang and Yizhe Yang and Chong Feng and Yang Gao}, year = {2024}, eprint = {2411.11681}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2411.11681v3}, }