Simulating Couple Conflict: Designing A Multi-Agent System for Therapy Training and Practice

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Canwen, Chen, Angela, Bao, Catherine, Jin, Siwei, Swartz, Holly, Wu, Tongshuang, Kraut, Robert E, Zhu, Haiyi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908934084755456
author Wang, Canwen
Chen, Angela
Bao, Catherine
Jin, Siwei
Swartz, Holly
Wu, Tongshuang
Kraut, Robert E
Zhu, Haiyi
author_facet Wang, Canwen
Chen, Angela
Bao, Catherine
Jin, Siwei
Swartz, Holly
Wu, Tongshuang
Kraut, Robert E
Zhu, Haiyi
contents Couples therapy requires managing complex, evolving emotional dynamics between partners, but traditional training methods for therapists, like role-play, lack realism, consistency, and control. We present a multi-modal simulation that models therapy as a controlled, multi-agent dynamical system with structured interaction stages. Therapists practice with a pair of client-agents who go through six evolving stages that respond to therapist actions. This simulation enables practice with demand-withdraw conflict patterns in a closed-loop environment. The simulation uses a sense-plan-act architecture: it detects the therapist's input, updates agents' interaction states based on psychotherapy theory and transcript analysis, and generates realistic verbal and emotional responses. In an experiment with 21 licensed U.S. therapists, participants more accurately identified state transitions and rated the system as more realistic and responsive than a prompt-based baseline, demonstrating the value of stateful, interpretable simulation for therapist training.
format Preprint
id arxiv_https___arxiv_org_abs_2601_10970
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Simulating Couple Conflict: Designing A Multi-Agent System for Therapy Training and Practice
Wang, Canwen
Chen, Angela
Bao, Catherine
Jin, Siwei
Swartz, Holly
Wu, Tongshuang
Kraut, Robert E
Zhu, Haiyi
Computers and Society
Human-Computer Interaction
Couples therapy requires managing complex, evolving emotional dynamics between partners, but traditional training methods for therapists, like role-play, lack realism, consistency, and control. We present a multi-modal simulation that models therapy as a controlled, multi-agent dynamical system with structured interaction stages. Therapists practice with a pair of client-agents who go through six evolving stages that respond to therapist actions. This simulation enables practice with demand-withdraw conflict patterns in a closed-loop environment. The simulation uses a sense-plan-act architecture: it detects the therapist's input, updates agents' interaction states based on psychotherapy theory and transcript analysis, and generates realistic verbal and emotional responses. In an experiment with 21 licensed U.S. therapists, participants more accurately identified state transitions and rated the system as more realistic and responsive than a prompt-based baseline, demonstrating the value of stateful, interpretable simulation for therapist training.
title Simulating Couple Conflict: Designing A Multi-Agent System for Therapy Training and Practice
topic Computers and Society
Human-Computer Interaction
url https://arxiv.org/abs/2601.10970