Tell Me: An LLM-powered Mental Well-being Assistant with RAG, Synthetic Dialogue Generation, and Agentic Planning

TL;DR

Tell Me is a comprehensive mental well-being system utilizing LLMs, RAG, synthetic dialogue, and agentic planning to provide personalized, accessible support and facilitate research, aiming to enhance mental health resources and emotional processing.

Contribution

The paper introduces a novel integrated system combining RAG, synthetic dialogues, and agentic planning for mental well-being support, addressing data scarcity and personalization challenges.

Findings

RAG assistant performs well in well-being scenarios based on automatic and human evaluations.

Synthetic client-therapist dialogues enable research and data augmentation.

The agentic planner offers dynamic, personalized self-care plans.

Abstract

We present Tell Me, a mental well-being system that leverages advances in large language models to provide accessible, context-aware support for users and researchers. The system integrates three components: (i) a retrieval-augmented generation (RAG) assistant for personalized, knowledge-grounded dialogue; (ii) a synthetic client-therapist dialogue generator conditioned on client profiles to facilitate research on therapeutic language and data augmentation; and (iii) a Well-being AI crew, implemented with CrewAI, that produces weekly self-care plans and guided meditation audio. The system is designed as a reflective space for emotional processing rather than a substitute for professional therapy. It illustrates how conversational assistants can lower barriers to support, complement existing care, and broaden access to mental health resources. To address the shortage of confidential therapeutic data, we introduce synthetic client-therapist dialogue generation conditioned on client profiles. Finally, the planner demonstrates an innovative agentic workflow for dynamically adaptive, personalized self-care, bridging the limitations of static well-being tools. We describe the architecture, demonstrate its functionalities, and report evaluation of the RAG assistant in curated well-being scenarios using both automatic LLM-based judgments and a human-user study. This work highlights opportunities for interdisciplinary collaboration between NLP researchers and mental health professionals to advance responsible innovation in human-AI interaction for well-being.