ProAI: Proactive Multi-Agent Conversational AI with Structured Knowledge Base for Psychiatric Diagnosis

2025-02-28

AI Summary

Current conversational AI systems are predominantly reactive, limiting their applicability in clinical tasks requiring proactive guidance—such as psychiatric diagnosis. This paper proposes an active, multi-agent dialogue system tailored for psychiatric differential diagnosis, departing from conventional large language model (LLM) paradigms. Our approach introduces a memory-goal joint reasoning framework augmented by a structured knowledge graph, a diagnosis-driven dialogue orchestration mechanism, and a collaborative multi-agent clinical interview architecture. Additionally, we integrate clinical guideline-aligned prompt engineering to ensure domain fidelity. The system undergoes rigorous validation via simulated patient interactions, user experience evaluation, and expert blind review. In psychiatric differential diagnosis, it achieves 83.3% accuracy—significantly outperforming baseline models—while satisfying stringent requirements for clinical professionalism, logical coherence, and empathetic interaction.

Technology Category

• Natural Language Processing: Conversational AI/Dialog Systems
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Most LLM-driven conversational AI systems operate reactively, responding to user prompts without guiding the interaction. Most LLM-driven conversational AI systems operate reactively, responding to user prompts without guiding the interaction. However, many real-world applications-such as psychiatric diagnosis, consulting, and interviews-require AI to take a proactive role, asking the right questions and steering conversations toward specific objectives. Using mental health differential diagnosis as an application context, we introduce ProAI, a goal-oriented, proactive conversational AI framework. ProAI integrates structured knowledge-guided memory, multi-agent proactive reasoning, and a multi-faceted evaluation strategy, enabling LLMs to engage in clinician-style diagnostic reasoning rather than simple response generation. Through simulated patient interactions, user experience assessment, and professional clinical validation, we demonstrate that ProAI achieves up to 83.3% accuracy in mental disorder differential diagnosis while maintaining professional and empathetic interaction standards. These results highlight the potential for more reliable, adaptive, and goal-driven AI diagnostic assistants, advancing LLMs beyond reactive dialogue systems.

Problem

• Proactive AI for psychiatric diagnosis
• Structured knowledge-guided memory integration
• Multi-agent reasoning for clinician-style diagnostics

Innovation

• Proactive conversational AI framework
• Structured knowledge-guided memory integration
• Multi-agent proactive reasoning system