@article{gagpogeneralizedadvantagegroupedpolicyop, title = {GAGPO: Generalized Advantage Grouped Policy Optimization}, author = {Siyuan Zhu and Chao Yu and Rongxin Yang and Zongkai Liu and Jinjun Hu and Qiwen Chen and Yibo Zhang}, year = {2026}, eprint = {2605.13217}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.13217}, }