@article{spiralselfplayonzerosumgames,
  title = {SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning},
  author = {Bo Liu and Leon Guertler and Simon Yu and Zichen Liu and Penghui Qi and Daniel Balcells and Mickel Liu and Cheston Tan and Weiyan Shi and Min Lin and Wee Sun Lee and Natasha Jaques},
  year = {2025},
  eprint = {2506.24119},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2506.24119v2},
}