@inproceedings{li-etal-2025-chatsop,
    title = "{C}hat{SOP}: An {SOP}-Guided {MCTS} Planning Framework for Controllable {LLM} Dialogue Agents",
    author = "Li, Zhigen  and
      Peng, Jianxiang  and
      Wang, Yanmeng  and
      Cao, Yong  and
      Shen, Tianhao  and
      Zhang, Minghui  and
      Su, Linxi  and
      Wu, Shang  and
      Wu, Yihang  and
      Wang, YuQian  and
      Wang, Ye  and
      Hu, Wei  and
      Li, Jianfeng  and
      Wang, Shaojun  and
      Xiao, Jing  and
      Xiong, Deyi",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.863/",
    pages = "17637--17659",
    ISBN = "979-8-89176-251-0",
    abstract = "Dialogue agents powered by Large Language Models (LLMs) show superior performance in various tasks. Despite the better user understanding and human-like responses, their **lack of controllability** remains a key challenge, often leading to unfocused conversations or task failure. To address this, we introduce Standard Operating Procedure (SOP) to regulate dialogue flow. Specifically, we propose **ChatSOP**, a novel SOP-guided Monte Carlo Tree Search (MCTS) planning framework designed to enhance the controllability of LLM-driven dialogue agents. To enable this, we curate a dataset comprising SOP-annotated multi-scenario dialogues, generated using a semi-automated role-playing system with GPT-4o and validated through strict manual quality control. Additionally, we propose a novel method that integrates Chain of Thought reasoning with supervised fine-tuning for SOP prediction and utilizes SOP-guided Monte Carlo Tree Search for optimal action planning during dialogues. Experimental results demonstrate the effectiveness of our method, such as achieving a 27.95{\%} improvement in action accuracy compared to baseline models based on GPT-3.5 and also showing notable gains for open-source models. Dataset and codes are publicly available."
}