@inproceedings{yang-etal-2026-metro,
    title = "{METRO}: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues",
    author = "Yang, Haofu  and
      Liu, Jiaji  and
      Huang, Chen  and
      Wu, Faguo  and
      Lei, Wenqiang  and
      Ng, See-Kiong",
    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.978/",
    pages = "21385--21416",
    ISBN = "979-8-89176-390-6",
    abstract = "Developing non-collaborative dialogue agents traditionally requires the manual, unscalable codification of expert strategies. We propose METRO, a method that leverages large language models to autonomously induce both strategy actions and planning logic directly from raw transcripts. METRO formalizes expert knowledge into a Strategy Forest, a hierarchical structure that captures both short-term responses (nodes) and long-term strategic foresight (branches). Experimental results across two benchmarks show that METRO demonstrates promising performance, outperforming existing methods by an average of 9{\%}-10{\%}. Our further analysis not only reveals the success behind METRO (strategic behavioral diversity and foresight), but also demonstrates its robust cross-task transferability. This offers new insights into building non-collaborative agents in a cost-effective and scalable way. Our code is available at https://github.com/Humphrey-0125/METRO."
}