CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration

2025-02-05

AI Summary

To address the imbalance between supply and demand in mental health services and the difficulty of intervening in ambivalence during behavior change, this paper introduces CAMI—the first automated counseling agent designed for Motivational Interviewing (MI). CAMI implements the STAR framework to achieve deep coupling of client psychological state inference and motivational topic exploration within an LLM-based system. It integrates a psychological state classifier, a topic evolution module, and an MI-compliant response generator, and employs closed-loop evaluation via simulated clients. Experiments demonstrate that CAMI significantly outperforms baselines in MI skill scoring, psychological state recognition accuracy (+12.3%), and topic exploration effectiveness. Human evaluations confirm its responses are more natural and empathetic, with higher precision in empathy expression, and validate its cross-cultural and cross-context applicability.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Multiagent Systems: Agent Communication
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• 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: Psychology-informed user models and recommender systems

Abstract

Conversational counselor agents have become essential tools for addressing the rising demand for scalable and accessible mental health support. This paper introduces CAMI, a novel automated counselor agent grounded in Motivational Interviewing (MI) -- a client-centered counseling approach designed to address ambivalence and facilitate behavior change. CAMI employs a novel STAR framework, consisting of client's state inference, motivation topic exploration, and response generation modules, leveraging large language models (LLMs). These components work together to evoke change talk, aligning with MI principles and improving counseling outcomes for clients from diverse backgrounds. We evaluate CAMI's performance through both automated and manual evaluations, utilizing simulated clients to assess MI skill competency, client's state inference accuracy, topic exploration proficiency, and overall counseling success. Results show that CAMI not only outperforms several state-of-the-art methods but also shows more realistic counselor-like behavior. Additionally, our ablation study underscores the critical roles of state inference and topic exploration in achieving this performance.

Problem

• Automated counselor agent for mental health
• State inference and topic exploration
• Improving counseling outcomes with LLMs

Innovation

• Utilizes large language models
• Incorporates state inference module
• Implements topic exploration strategy