@article{epoexplicitpolicyoptimizationfor,
  title = {EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning},
  author = {Xiaoqian Liu and Ke Wang and Yongbin Li and Yuchuan Wu and Wentao Ma and Aobo Kong and Fei Huang and Jianbin Jiao and Junge Zhang},
  year = {2025},
  eprint = {2502.12486},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.12486v3},
}