@inproceedings{yang-etal-2026-tournament,
    title = "Tournament-{GRPO}: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation",
    author = "Yang, Zixuan  and
      Chen, Yiqun  and
      Yang, Wei  and
      Zhang, Erhan  and
      Shen, Zihan  and
      Wei, Xiaochi  and
      Gao, Yan  and
      Wu, Yi  and
      Hu, Yao  and
      Mao, Jiaxin",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1515/",
    pages = "34556--34573",
    ISBN = "979-8-89176-459-0"
}