@article{unifyinggrouprelativeandselfdistillation, title = {Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing}, author = {Gengsheng Li and Tianyu Yang and Junfeng Fang and Mingyang Song and Mao Zheng and Haiyun Guo and Dan Zhang and Jinqiao Wang and Tat-Seng Chua}, year = {2026}, eprint = {2604.02288}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.02288}, }