@article{msrlscalinggenerativemultimodalrewardmod,
  title = {MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning},
  author = {Chenglong Wang and Yifu Huo and Yang Gan and Qiaozhi He and Qi Meng and Bei Li and Yan Wang and Junfu Liu and Tianhua Zhou and Jingbo Zhu and Tong Xiao},
  year = {2026},
  eprint = {2603.25108},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.25108},
}