@article{prpoaligningprocessrewardwithoutcomerewa, title = {PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization}, author = {Ruiyi Ding and Yongxuan Lv and Xianhui Meng and Jiahe Song and Chao Wang and Chen Jiang and Yuan Cheng}, year = {2026}, eprint = {2601.07182}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2601.07182}, }