MindfulAgents: Personalizing Mindfulness Meditation via an Expert-Aligned Multi-Agent System

2026-03-06

AI Summary

This study addresses the limitations of existing mindfulness meditation applications, which often struggle to sustain long-term user engagement due to a lack of personalization and reliance on costly human intervention. To overcome these challenges, this work proposes a novel large language model–based multi-agent system that integrates an expert-aligned mindfulness framework with a multi-agent architecture. The system enables low-cost, scalable personalized meditation guidance through real-time user feedback and adaptive content generation. In a laboratory study (N=13), the system significantly enhanced users’ focus and self-awareness while reducing immediate stress. These findings were further corroborated by a four-week deployment study (N=62), which demonstrated the system’s effectiveness in improving both sustained engagement and overall mindfulness levels over time.

Technology Category

• Multiagent Systems: Applications
• Cognitive Modeling & Cognitive Systems: Applications
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Mindfulness meditation is a widely accessible and evidence-based method for supporting mental health. Despite the proliferation of mindfulness meditation apps, sustaining user engagement remains a persistent challenge. Personalizing the meditation experience is a promising strategy to improve engagement, but it often requires costly and unscalable manual effort. We present MindfulAgents, a multi-agent system powered by large language models that (1) generates guided meditation scripts based on an expert-established mindfulness framework, (2) encourages users'reflection on emotional states and mindfulness skills, and (3) enables real-time personalization of the mindfulness meditation experience for each user. In a formative lab study (N=13), MindfulAgents significantly improved in-session engagement (p = 0.011) and self-awareness (p = 0.014), and reduced momentary stress (p = 0.020). Furthermore, a four-week deployment study (N=62) demonstrated a notable increase in long-term engagement (p = 0.002) and level of mindfulness (p = 0.023). Participants reported that MindfulAgents offered more relevant meditation sessions personalized to individual needs in various contexts, supporting sustained practice. Our findings highlight the potential of LLM-driven personalization for enhancing user engagement in digital mindfulness meditation interventions.

Problem

• mindfulness meditation
• personalization
• user engagement
• digital intervention
• scalability

Innovation

• multi-agent system
• large language models
• personalized mindfulness
• real-time personalization
• digital mental health