@article{onewaypolicyoptimizationforselfevolvingl,
  title = {One-Way Policy Optimization for Self-Evolving LLMs},
  author = {Shuo Yang and Jinda Lu and Kexin Huang and Chiyu Ma and Shaohang Wei and Yuyang Liu and Guoyin Wang and Jingren Zhou and Li Yuan},
  year = {2026},
  eprint = {2605.22156},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.22156},
}