@article{coopercooptimizingpolicyandrewardmodelsi,
  title = {Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models},
  author = {Haitao Hong and Yuchen Yan and Xingyu Wu and Guiyang Hou and Wenqi Zhang and Weiming Lu and Yongliang Shen and Jun Xiao},
  year = {2025},
  eprint = {2508.05613},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.05613},
}