AgentMental: An Interactive Multi-Agent Framework for Explainable and Adaptive Mental Health Assessment

2025-08-15

AI Summary

Clinical psychological assessment suffers from low accessibility due to shortages of trained professionals, while existing AI approaches rely on static text analysis and fail to capture dynamic, context-sensitive behavioral cues. To address this, we propose an interpretable, adaptive multi-agent conversational assessment framework that simulates clinician–patient interactions. It employs a tree-structured memory to maintain context-aware symptom representation and implements an adaptive questioning mechanism that dynamically generates personalized follow-up questions based on user responses—enabling real-time response adequacy evaluation and iterative clinical probing. Integrating dynamic interaction policies with response-conditioned question generation, our method achieves significant improvements over state-of-the-art static models on the DAIC-WOZ dataset: higher symptom identification accuracy, enhanced information extraction completeness, and improved dialogue coherence. This work establishes a new paradigm for automated mental health assessment that balances interpretability, clinical relevance, and adaptive reasoning.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Natural Language Processing: Conversational AI/Dialog Systems
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• 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: User modeling and simulation for interactive and conversational systems

Abstract

Mental health assessment is crucial for early intervention and effective treatment, yet traditional clinician-based approaches are limited by the shortage of qualified professionals. Recent advances in artificial intelligence have sparked growing interest in automated psychological assessment, yet most existing approaches are constrained by their reliance on static text analysis, limiting their ability to capture deeper and more informative insights that emerge through dynamic interaction and iterative questioning. Therefore, in this paper, we propose a multi-agent framework for mental health evaluation that simulates clinical doctor-patient dialogues, with specialized agents assigned to questioning, adequacy evaluation, scoring, and updating. We introduce an adaptive questioning mechanism in which an evaluation agent assesses the adequacy of user responses to determine the necessity of generating targeted follow-up queries to address ambiguity and missing information. Additionally, we employ a tree-structured memory in which the root node encodes the user's basic information, while child nodes (e.g., topic and statement) organize key information according to distinct symptom categories and interaction turns. This memory is dynamically updated throughout the interaction to reduce redundant questioning and further enhance the information extraction and contextual tracking capabilities. Experimental results on the DAIC-WOZ dataset illustrate the effectiveness of our proposed method, which achieves better performance than existing approaches.

Problem

• Automated mental health assessment lacks dynamic interaction capabilities
• Traditional methods struggle with ambiguity and missing information
• Existing approaches fail to adaptively update user response evaluations

Innovation

• Multi-agent framework simulating clinical dialogues
• Adaptive questioning mechanism for ambiguity resolution
• Tree-structured memory for dynamic information organization