MindfulAgents: Personalizing Mindfulness Meditation via an Expert-Aligned Multi-Agent System
This addresses the problem of low engagement in digital mindfulness interventions for mental health users, representing an incremental advance in personalization methods.
The paper tackles the challenge of sustaining user engagement in mindfulness meditation apps by developing MindfulAgents, a multi-agent system using large language models to personalize meditation experiences. Results from studies with 13 and 62 participants showed significant improvements in engagement, self-awareness, stress reduction, and mindfulness levels.
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.