@inproceedings{kim-etal-2025-principles,
    title = "{PRINCIPLES}: Synthetic Strategy Memory for Proactive Dialogue Agents",
    author = "Kim, Namyoung  and
      Ong, Kai Tzu-iunn  and
      Hwang, Yeonjun  and
      Kang, Minseok  and
      Jihn, Iiseo  and
      Kim, Gayoung  and
      Kim, Minju  and
      Yeo, Jinyoung",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.1164/",
    doi = "10.18653/v1/2025.findings-emnlp.1164",
    pages = "21329--21368",
    ISBN = "979-8-89176-335-7",
    abstract = "Dialogue agents based on large language models (LLMs) have shown promising performance in proactive dialogue, which requires effective strategy planning. However, existing approaches to strategy planning for proactive dialogue face several limitations: limited strategy coverage, preference bias in planning, and reliance on costly additional training. To address these, we propose PRINCIPLES: a synthetic strategy memory for proactive dialogue agents. PRINCIPLES is derived through offline self-play simulations and serves as reusable knowledge that guides strategy planning during inference, eliminating the need for additional training and data annotation. We evaluate PRINCIPLES in both emotional support and persuasion domains, demonstrating consistent improvements over strong baselines. Furthermore, PRINCIPLES maintains its robustness across extended and more diverse evaluation settings. See our project page at https://huggingface.co/spaces/kimnamssya/Principles."
}