@inproceedings{jiao-etal-2026-policy,
    title = "Policy of Thoughts: Scaling {LLM} Reasoning via Test-time Policy Evolution",
    author = "Jiao, Zhengbo  and
      Xian, Hongyu  and
      Wang, Qinglong  and
      Ma, Yunpu  and
      Wang, Zhebo  and
      Kong, Dezhang  and
      Han, Meng",
    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.1908/",
    pages = "43472--43490",
    ISBN = "979-8-89176-459-0"
}