@article{reflectivepolicyoptimization,
  title = {Reflective Policy Optimization},
  author = {Yaozhong Gan and Renye Yan and Zhe Wu and Junliang Xing},
  year = {2024},
  eprint = {2406.03678},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.03678v1},
}