Scholarlink

Recent progress in natural language processing has created new possibilities for delivering personalized digital mental health support. Yet, combining structured, evidence-based therapeutic frameworks with the flexibility of natural conversation remains a challenge. This study examines the use of Large Language Models (LLMs) in structured chatbots to improve delivery of the World Health Organization’s Self-Help+ program. We compared a conventional state-machine chatbot with an LLM-enhanced version and finally with a multi-agent architecture, examining the strengths and limitations of the different approaches. Through simulation testing and expert focus group analysis, we found that a multi-agent architecture, while significantly improving personalization, struggles in maintaining protocol fidelity and therapeutic structure. Our findings suggest that current LLM-based architectures, while promising, might not yet be ready for unsupervised deployment in mental health contexts.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Are We Ready for Multi-agent Systems to Deliver Structured Mental Health Support? Lessons from Adapting Self-Help+ Intervention

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Leonardo Sanna,
  • Marco Bolpagni,
  • Valentina Fietta,
  • Simone De Carli,
  • Mattia Franzin,
  • Giorgia Gavioli,
  • Lorenzo Gios,
  • Susanna Pardini,
  • Anna Elena Nicoletti,
  • Silvia Rizzi,
  • Silvia Gabrielli,
  • Mauro Dragoni

摘要

Recent progress in natural language processing has created new possibilities for delivering personalized digital mental health support. Yet, combining structured, evidence-based therapeutic frameworks with the flexibility of natural conversation remains a challenge. This study examines the use of Large Language Models (LLMs) in structured chatbots to improve delivery of the World Health Organization’s Self-Help+ program. We compared a conventional state-machine chatbot with an LLM-enhanced version and finally with a multi-agent architecture, examining the strengths and limitations of the different approaches. Through simulation testing and expert focus group analysis, we found that a multi-agent architecture, while significantly improving personalization, struggles in maintaining protocol fidelity and therapeutic structure. Our findings suggest that current LLM-based architectures, while promising, might not yet be ready for unsupervised deployment in mental health contexts.