A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation

TL;DR

This paper introduces a multi-agent LLM framework with safety and role differentiation to simulate supportive behavioral health conversations, emphasizing safety, interpretability, and system design.

Contribution

It presents a novel multi-agent architecture with role-based specialization and safety oversight for behavioral health dialogue simulation.

Findings

Agents demonstrate clear role differentiation and coordination.

The framework maintains safety and coherence in conversations.

Trade-offs between modularity, safety, and response latency are characterized.

Abstract

Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversational functions and maintain safety in behavioral health communication. We propose a safety-aware, role-orchestrated multi-agent LLM framework designed to simulate supportive behavioral health dialogue through coordinated, role-differentiated agents. Conversational responsibilities are decomposed across specialized agents, including empathy-focused, action-oriented, and supervisory roles, while a prompt-based controller dynamically activates relevant agents and enforces continuous safety auditing. Using semi-structured interview transcripts from the DAIC-WOZ corpus, we evaluate the framework with scalable proxy metrics capturing structural quality, functional diversity, and computational characteristics. Results illustrate clear role differentiation, coherent inter-agent coordination, and predictable trade-offs between modular orchestration, safety oversight, and response latency when compared to a single-agent baseline. This work emphasizes system design, interpretability, and safety, positioning the framework as a simulation and analysis tool for behavioral health informatics and decision-support research rather than a clinical intervention.