@article{reflectrmboostinggenerativerewardmodelsv, title = {ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework}, author = {Kai Qin and Liangxin Liu and Yu Liang and Longzheng Wang and Yan Wang and Yueyang Zhang and Long Xia and Zhiyuan Sun and Houde Liu and Daiting Shi}, year = {2026}, eprint = {2604.07506}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2604.07506}, }