MindfulAgents: Personalizing Mindfulness Meditation via an Expert-Aligned Multi-Agent System
Mengyuan Millie Wu, Zhihan Jiang, Yuang Fan, Richard Feng, Sahiti Dharmavaram, Mathew Polowitz, Shawn Fallon, Bashima Islam, Lizbeth Benson, Irene Tung, David Creswell, Xuhai Xu
arXiv Preprint Archive March 6, 2026 via arXiv
Summary
AI-generated from the abstractA multi-agent system called MindfulAgents uses large language models to generate guided meditation scripts, encourage reflection on emotional states, and personalize meditation in real time. In a lab study with 13 participants, it improved in-session engagement, self-awareness, and reduced momentary stress. A four-week deployment with 62 participants showed increased long-term engagement and level of mindfulness. Participants reported that the system offered more relevant meditation sessions tailored to individual needs, supporting sustained practice. The findings highlight the potential of LLM-driven personalization for digital mindfulness interventions.
Study at a glance
| Characteristics | Formative lab study and four-week deployment study Peer reviewed |
|---|---|
| Sample size | 75 |
| Population | Participants in a lab study (N=13) and a four-week deployment study (N=62) |
| Duration | Four-week deployment |
| Keywords | Cs.hc Cs.ai |
| Key finding | MindfulAgents significantly improved in-session engagement, self-awareness, reduced momentary stress, and increased long-term engagement and level of mindfulness. |
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.