@inproceedings{qiu-lan-2026-interactive,
title = "Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing {LLM}-to-{LLM} Interactions",
author = "Qiu, Huachuan and
Lan, Zhenzhong",
editor = "Mohammad, Saif M. and
Ousidhoum, Nedjma",
booktitle = "Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*{SEM} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.starsem-conference.29/",
pages = "410--427",
ISBN = "979-8-89176-413-2",
abstract = "Creating effective dialogue systems for mental health support requires high-quality multi-turn counseling dialogue data, yet collecting real counselor-client conversations presents significant challenges, including privacy concerns, high costs, and limited scalability. We present \textbf{Interactive Agents}, a novel framework that simulates naturalistic counseling dialogues through controlled LLM-to-LLM interactions. The framework introduces two key innovations: (1) a personalized client agent that maintains consistent psychological characteristics throughout a session, and (2) a counselor agent that implements a theoretically grounded three-stage therapeutic model comprising the exploration, insight, and action phases. Through rigorous evaluation using both automatic metrics and professional-counselor assessments based on the Working Alliance Inventory, we demonstrate that our framework generates therapeutically valid dialogues that are comparable in quality to human-generated sessions. Models fine-tuned on our proposed synthetic dataset (SimPsyDial) achieve state-of-the-art performance in a standard pairwise chatbot-arena evaluation of LLM-based counselors. Our framework provides a scalable, privacy-preserving method for generating high-quality counseling dialogue data while maintaining professional therapeutic standards."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-lan-2026-interactive">
<titleInfo>
<title>Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huachuan</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenzhong</namePart>
<namePart type="family">Lan</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>Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nedjma</namePart>
<namePart type="family">Ousidhoum</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">979-8-89176-413-2</identifier>
</relatedItem>
<abstract>Creating effective dialogue systems for mental health support requires high-quality multi-turn counseling dialogue data, yet collecting real counselor-client conversations presents significant challenges, including privacy concerns, high costs, and limited scalability. We present Interactive Agents, a novel framework that simulates naturalistic counseling dialogues through controlled LLM-to-LLM interactions. The framework introduces two key innovations: (1) a personalized client agent that maintains consistent psychological characteristics throughout a session, and (2) a counselor agent that implements a theoretically grounded three-stage therapeutic model comprising the exploration, insight, and action phases. Through rigorous evaluation using both automatic metrics and professional-counselor assessments based on the Working Alliance Inventory, we demonstrate that our framework generates therapeutically valid dialogues that are comparable in quality to human-generated sessions. Models fine-tuned on our proposed synthetic dataset (SimPsyDial) achieve state-of-the-art performance in a standard pairwise chatbot-arena evaluation of LLM-based counselors. Our framework provides a scalable, privacy-preserving method for generating high-quality counseling dialogue data while maintaining professional therapeutic standards.</abstract>
<identifier type="citekey">qiu-lan-2026-interactive</identifier>
<location>
<url>https://aclanthology.org/2026.starsem-conference.29/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>410</start>
<end>427</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions
%A Qiu, Huachuan
%A Lan, Zhenzhong
%Y Mohammad, Saif M.
%Y Ousidhoum, Nedjma
%S Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-413-2
%F qiu-lan-2026-interactive
%X Creating effective dialogue systems for mental health support requires high-quality multi-turn counseling dialogue data, yet collecting real counselor-client conversations presents significant challenges, including privacy concerns, high costs, and limited scalability. We present Interactive Agents, a novel framework that simulates naturalistic counseling dialogues through controlled LLM-to-LLM interactions. The framework introduces two key innovations: (1) a personalized client agent that maintains consistent psychological characteristics throughout a session, and (2) a counselor agent that implements a theoretically grounded three-stage therapeutic model comprising the exploration, insight, and action phases. Through rigorous evaluation using both automatic metrics and professional-counselor assessments based on the Working Alliance Inventory, we demonstrate that our framework generates therapeutically valid dialogues that are comparable in quality to human-generated sessions. Models fine-tuned on our proposed synthetic dataset (SimPsyDial) achieve state-of-the-art performance in a standard pairwise chatbot-arena evaluation of LLM-based counselors. Our framework provides a scalable, privacy-preserving method for generating high-quality counseling dialogue data while maintaining professional therapeutic standards.
%U https://aclanthology.org/2026.starsem-conference.29/
%P 410-427
Markdown (Informal)
[Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions](https://aclanthology.org/2026.starsem-conference.29/) (Qiu & Lan, *SEM 2026)
ACL