@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2026-psychain">
<titleInfo>
<title>PsyChain: A Collaborative Chain-of-Agents Framework for Generating Personalized and Professional Counseling Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijie</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenxuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liping</namePart>
<namePart type="family">Jing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<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 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 PsyChainD, a Chinese dataset of 10,456 dialogues featuring systematically diverse client profiles. Extensive evaluation across client side, counselor side and 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.</abstract>
<identifier type="citekey">feng-etal-2026-psychain</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1831/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>36757</start>
<end>36791</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PsyChain: A Collaborative Chain-of-Agents Framework for Generating Personalized and Professional Counseling Dialogues
%A Feng, Yi
%A Yang, Zijie
%A Zhang, Chen
%A Zhang, Wenxuan
%A Zhang, Dongming
%A Jing, Liping
%A Yu, Jian
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F feng-etal-2026-psychain
%X 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 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 PsyChainD, a Chinese dataset of 10,456 dialogues featuring systematically diverse client profiles. Extensive evaluation across client side, counselor side and 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.
%U https://aclanthology.org/2026.findings-acl.1831/
%P 36757-36791
Markdown (Informal)
[PsyChain: A Collaborative Chain-of-Agents Framework for Generating Personalized and Professional Counseling Dialogues](https://aclanthology.org/2026.findings-acl.1831/) (Feng et al., Findings 2026)
ACL
- Yi Feng, Zijie Yang, Chen Zhang, Wenxuan Zhang, Dongming Zhang, Liping Jing, and Jian Yu. 2026. PsyChain: A Collaborative Chain-of-Agents Framework for Generating Personalized and Professional Counseling Dialogues. In Findings of the Association for Computational Linguistics: ACL 2026, pages 36757–36791, San Diego, California, United States. Association for Computational Linguistics.