@inproceedings{dai-etal-2026-small,
    title = "Small {RL} Controller, Large Language Model: {RL}-Guided Adaptive Sampling for Test-Time Scaling",
    author = "Dai, Runpeng  and
      Zheng, Tong  and
      Liu, Rui  and
      Huang, Chengsong  and
      Zhu, Hongtu",
    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.1670/",
    pages = "37985--37999",
    ISBN = "979-8-89176-459-0"
}