@article{graphpographbasedpolicyoptimizationforre, title = {GraphPO: Graph-based Policy Optimization for Reasoning Models}, author = {Yuliang Zhan and Xinyu Tang and Jian Li and Dandan Zheng and Weilong Chai and Jingdong Chen and Jun Zhou and Ge Wu and Wenyue Tang and Hao Sun}, year = {2026}, eprint = {2606.18954}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.18954}, }