@article{gapolearningpreferentialpromptthrough,
  title = {GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization},
  author = {Zhouhong Gu and Xingzhou Chen and Xiaoran Shi and Tao Wang and SuHang Zheng and Tianyu Li and Hongwei Feng and Yanghua Xiao},
  year = {2025},
  eprint = {2503.20194},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.20194v1},
}