@article{spellselfplayreinforcementlearningforevo,
  title = {SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models},
  author = {Ziyi Yang and Weizhou Shen and Chenliang Li and Ruijun Chen and Fanqi Wan and Ming Yan and Xiaojun Quan and Fei Huang},
  year = {2025},
  eprint = {2509.23863},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.23863},
}