Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions

Huachuan Qiu, Zhenzhong Lan


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.
Anthology ID:
2026.starsem-conference.29
Volume:
Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026)
Month:
July
Year:
2026
Address:
San Diego, California, United States
Editors:
Saif M. Mohammad, Nedjma Ousidhoum
Venues:
*SEM | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
410–427
Language:
URL:
https://preview.aclanthology.org/ingest-acl-workshops/2026.starsem-conference.29/
DOI:
Bibkey:
Cite (ACL):
Huachuan Qiu and Zhenzhong Lan. 2026. Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions. In Proceedings of the 15th Joint Conference on Lexical and Computational Semantics (*SEM 2026), pages 410–427, San Diego, California, United States. Association for Computational Linguistics.
Cite (Informal):
Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions (Qiu & Lan, *SEM 2026)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-workshops/2026.starsem-conference.29.pdf