多智能体框架模拟心理健康对话，分工协作更安全。
A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation
- 分角色智能体协同：共情、行动、监督三类角色分工明确。
- 相比单智能体，对话结构更优，安全审计持续运行。
- 适合研究心理干预模拟，非临床直接应用。
单智能体大语言模型在心理健康对话中难以兼顾多样功能与安全性。本文提出一种安全感知、角色协同的多智能体框架，通过专业化分工（共情型、行动型、监督型）实现支持性对话模拟，并由基于提示的控制器动态调度智能体，持续执行安全审计。基于DAIC-WOZ语料库的半结构化访谈数据，采用可扩展的代理指标评估框架的结构质量、功能多样性与计算特性。结果表明：各角色区分清晰，智能体间协调连贯，在模块化编排、安全监控与响应延迟之间存在可预测的权衡关系，优于单智能体基线。该工作强调系统设计、可解释性与安全性，定位为行为健康信息学与决策支持研究的仿真分析工具，而非临床干预手段。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。