Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions
🤖 AI Summary
Existing evaluation of health-coaching dialogue agents suffers from a lack of high-fidelity synthetic users. Method: We propose an end-to-end framework that jointly models clinical-grade health conditions (e.g., insomnia, diabetes) with real-world behavioral data to generate structured health behavior representations and fine-grained user profiles; subsequently, we simulate realistic interactions via the Concordia generative agent architecture and LLM-driven prompting. Contribution/Results: This work introduces the first joint modeling of clinical health states and multidimensional behavioral features, significantly enhancing synthetic users’ fidelity in need comprehension and challenge articulation. In two case studies, coaching agents achieved a 37% improvement in user-need understanding accuracy. Multi-expert blind evaluation rated synthetic user fidelity at 92% relative to real users—substantially outperforming all baselines.
Application Category
📝 Abstract
We present an end-to-end framework for generating synthetic users for evaluating interactive agents designed to encourage positive behavior changes, such as in health and lifestyle coaching. The synthetic users are grounded in health and lifestyle conditions, specifically sleep and diabetes management in this study, to ensure realistic interactions with the health coaching agent. Synthetic users are created in two stages: first, structured data are generated grounded in real-world health and lifestyle factors in addition to basic demographics and behavioral attributes; second, full profiles of the synthetic users are developed conditioned on the structured data. Interactions between synthetic users and the coaching agent are simulated using generative agent-based models such as Concordia, or directly by prompting a language model. Using two independently-developed agents for sleep and diabetes coaching as case studies, the validity of this framework is demonstrated by analyzing the coaching agent's understanding of the synthetic users' needs and challenges. Finally, through multiple blinded evaluations of user-coach interactions by human experts, we demonstrate that our synthetic users with health and behavioral attributes more accurately portray real human users with the same attributes, compared to generic synthetic users not grounded in such attributes. The proposed framework lays the foundation for efficient development of conversational agents through extensive, realistic, and grounded simulated interactions.
Problem
Research questions and friction points this paper is trying to address.
Generates synthetic users for health coaching evaluations
Simulates interactions using generative agent-based models
Validates framework with expert-evaluated user-coach interactions
Innovation
Methods, ideas, or system contributions that make the work stand out.
Generates synthetic users realistically
Uses agent-based models for simulation
Validates with expert-blind evaluations
🔎 Similar Papers
No similar papers found.
