Simulating Couple Conflict: Designing A Multi-Agent System for Therapy Training and Practice
This work provides a more realistic and controllable training tool for therapists, addressing limitations of traditional role-play methods.
The authors developed a multi-agent simulation for couples therapy training that models demand-withdraw conflict patterns through six evolving stages. In an experiment with 21 licensed therapists, the system outperformed a prompt-based baseline in state transition identification accuracy and realism ratings.
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.