AI RESEARCH

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

arXiv CS.AI

ArXi:2604.00249v1 Announce Type: new Single-agent large language model (LLM) systems struggle to simultaneously diverse conversational functions and maintain safety in behavioral health communication. We propose a safety-aware, role-orchestrated multi-agent LLM framework designed to simulate ive behavioral health dialogue through coordinated, role-differentiated agents.