@inproceedings{li-etal-2025-mads,
    title = "{MADS}: Multi-Agent Dialogue Simulation for Diverse Persuasion Data Generation",
    author = "Li, Mingjin  and
      Liu, Yu  and
      Liu, Huayi  and
      Ye, Xiang  and
      Jiang, Chao  and
      Zhang, Hongguang  and
      Ruan, Yu",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.emnlp-industry.26/",
    doi = "10.18653/v1/2025.emnlp-industry.26",
    pages = "399--415",
    ISBN = "979-8-89176-333-3",
    abstract = "We propose MADS (Multi-Agent Dialogue Simulation), a scalable framework for generating persuasive multi-turn dialogues via agent self-play. MADS employs three coordinated agents: User Agents designed to simulate diverse persona-driven behaviors by leveraging personality signifiers such as Zodiac Signs and MBTI types, a Dialog Agent executing task-oriented persuasion strategies and an Optimization Agent evaluating and refining dialogue outcomes. We further validate its effectiveness through users' Chain-of-Attitude (CoA) modeling and dedicated LLMs' persuasion assessment. This approach enables low-cost generation of training data without human annotation, addressing key industry challenges such as lack of user data, cold-start evaluation difficulties, and prompt inefficiency. Applied to a real-world marketing scenario, MADS significantly improved the persuasion capacity of small LLMs, increasing the organic traffic conversion rate by 22.4{\%} (from 1.83{\%} to 2.24{\%}) , demonstrating clear business value."
}