@inproceedings{zhou-etal-2026-beyond-stability,
    title = "Beyond the Stability-Exploration Dilemma: Environmental Regularization for {LLM} Policy Optimization",
    author = "Zhou, Xianlei  and
      Meng, Xiangdi  and
      He, Yu  and
      Qi, Tianyu  and
      Guan, Shuyan  and
      Zhang, Xianli  and
      Zhang, Jian  and
      Li, Xin  and
      Lin, Qika  and
      Liu, Jun",
    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.1586/",
    pages = "36071--36086",
    ISBN = "979-8-89176-459-0"
}