@inproceedings{zhang-etal-2026-towards,
    title = "Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts",
    author = "Zhang, Di  and
      Wu, Xun  and
      Huang, Shaohan  and
      Jiang, Lingjie  and
      Hao, Yaru  and
      Dong, Li  and
      Chi, Zewen  and
      Sui, Zhifang  and
      Wei, Furu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1165/",
    pages = "25446--25457",
    ISBN = "979-8-89176-390-6"
}