@inproceedings{feng-etal-2026-psychain,
    title = "{P}sy{C}hain: A Collaborative Chain-of-Agents Framework for Generating Personalized and Professional Counseling Dialogues",
    author = "Feng, Yi  and
      Yang, Zijie  and
      Zhang, Chen  and
      Zhang, Wenxuan  and
      Zhang, Dongming  and
      Jing, Liping  and
      Yu, Jian",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1831/",
    pages = "36757--36791",
    ISBN = "979-8-89176-395-1",
    abstract = "Existing psychological counseling datasets often suffer from monolithic client personas, insufficient therapeutic depth, and a lack of process controllability. To address these critical limitations, we propose \textbf{PsyChain}, a chain-of-agents framework that evolves static counseling corpora into high-fidelity dialogues through collaborative simulation which explicitly models client personality, stage progression, safety monitoring, and expert supervision. PsyChain involves a Client Profiler that extracts life scenarios and pairs them with psychological personality archetypes to synthesize diverse profiles.To simulate the complete counseling process, five specialized agents{---}Process Monitor, Client Speaker, Safety Monitor, Counselor Supervisor, and Counselor Speaker{---}collaborate and interact autonomously at each dialogue turn to ensure therapeutic professionalism and safety.We apply this to construct \textbf{PsyChainD}, a Chinese dataset of 10,456 dialogues featuring systematically diverse client profiles. Extensive evaluation across \textit{client side}, \textit{counselor side} and \textit{overall quality} shows substantial improvements. The model trained on PsyChainD achieves 61-91{\%} win rates against domain-specific baselines in pairwise evaluation and the highest average score in human evaluation, indicating potential for real-world counseling."
}