VChatter: Exploring Generative Conversational Agents for Simulating Exposure Therapy to Reduce Social Anxiety

2025-06-04

AI Summary

Clinical resources for social anxiety disorder (SAD) intervention are scarce, and constructing ecologically valid exposure scenarios is costly. Method: We propose VChatter, a large language model (LLM)-based multi-agent system featuring a hierarchical, exposure-oriented, multi-role agent architecture. It comprises a psychotherapist agent (Agent-P) that designs personalized, graded exposure protocols, and three exposure-intensity–tiered interaction agents (Agent-Hs: low/medium/high) that conduct role-play dialogues. The system integrates real-time user state perception and adaptive feedback mechanisms. Contribution/Results: A six-day qualitative study (N=10) demonstrated significant reductions in participants’ social anxiety, loneliness, and avoidance behaviors. Results validate the feasibility and preliminary efficacy of LLM agents in simulating evidence-based clinical exposure therapy, establishing a novel, scalable, and self-guided paradigm for digital mental health interventions.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Many people struggle with social anxiety, feeling fear, or even physically uncomfortable in social situations like talking to strangers. Exposure therapy, a clinical method that gradually and repeatedly exposes individuals to the source of their fear and helps them build coping mechanisms, can reduce social anxiety but traditionally requires human therapists' guidance and constructions of situations. In this paper, we developed a multi-agent system VChatter to explore large language models(LLMs)-based conversational agents for simulating exposure therapy with users. Based on a survey study (N=36) and an expert interview, VChatter includes an Agent-P, which acts as a psychotherapist to design the exposure therapy plans for users, and two Agent-Hs, which can take on different interactive roles in low, medium, and high exposure scenarios. A six-day qualitative study (N=10) showcases VChatter's usefulness in reducing users' social anxiety, feelings of isolation, and avoidance of social interactions. We demonstrated the feasibility of using LLMs-based conversational agents to simulate exposure therapy for addressing social anxiety and discussed future concerns for designing agents tailored to social anxiety.

Problem

• Simulating exposure therapy for social anxiety using conversational agents
• Reducing therapist dependency with AI-generated exposure scenarios
• Addressing social isolation through multi-agent LLM-based interactions

Innovation

• Multi-agent system simulating exposure therapy
• LLM-based conversational agents for anxiety reduction
• Therapist and interactive role agents in scenarios