Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Trishala Jayesh Ahalpara

TL;DR

Tell Me addresses core gaps in LLM-based mental well-being tools by integrating a retrieval-augmented dialogue agent, a profile-conditioned synthetic dialogue generator for safe data augmentation, and a CrewAI-driven well-being planner for adaptive self-care. The RAG-based assistant grounds conversations in a curated knowledge base with a sentiment safety prefilter, while the synthetic dialogue module enables researchers to generate customizable, confidential data. The system is evaluated via an automatic LLM-as-a-judge framework and a human study, showing retrieval grounding improves contextuality and empathy, with practical advantages in clarity and perceived usefulness. As an open, lightweight demo, Tell Me serves as a research testbed and pedagogical tool, fostering responsible, interdisciplinary development of AI-assisted well-being tools with safeguards and privacy-preserving design.

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.

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

TL;DR

Tell Me addresses core gaps in LLM-based mental well-being tools by integrating a retrieval-augmented dialogue agent, a profile-conditioned synthetic dialogue generator for safe data augmentation, and a CrewAI-driven well-being planner for adaptive self-care. The RAG-based assistant grounds conversations in a curated knowledge base with a sentiment safety prefilter, while the synthetic dialogue module enables researchers to generate customizable, confidential data. The system is evaluated via an automatic LLM-as-a-judge framework and a human study, showing retrieval grounding improves contextuality and empathy, with practical advantages in clarity and perceived usefulness. As an open, lightweight demo, Tell Me serves as a research testbed and pedagogical tool, fostering responsible, interdisciplinary development of AI-assisted well-being tools with safeguards and privacy-preserving design.

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.

Paper Structure

This paper contains 22 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Overview
  4. Tell Me RAG-based Assistant
  5. Data and Knowledge Base
  6. Embedding, Retrieval, and Context Management
  7. Modes of Operation
  8. Simulate a Conversation
  9. Well-being Planner
  10. Availability
  11. Tell Me Assistant Evaluation
  12. Benchmark Setup
  13. Prompts.
  14. Candidate models.
  15. LLM-as-a-Judge
  16. ...and 7 more sections

Figures (2)

  • Figure 1: System architecture of the Tell Me Mental Well-being Assistant, showing integration of RAG, synthetic dialogue generation, and agentic AI modules.
  • Figure 2: System architecture components of the Tell Me Mental Well-being Assistant: (a) synthetic conversation simulation; (b) CrewAI-based well-being planner.