Saved in:
Bibliographic Details
Main Author: Cho, Ha Na
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.00249
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914435893821440
author Cho, Ha Na
author_facet Cho, Ha Na
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00249
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation
Cho, Ha Na
Artificial Intelligence
Multiagent Systems
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.
title A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2604.00249