Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactions

TL;DR

This paper introduces a comprehensive framework for creating realistic synthetic users with health conditions to evaluate and improve health coaching agents through simulated interactions grounded in real-world data.

Contribution

It presents a novel end-to-end method for generating health-grounded synthetic users and simulating their interactions with coaching agents for evaluation purposes.

Findings

Synthetic users more accurately mimic real users with similar health attributes.

The framework enables extensive testing of coaching agents in realistic scenarios.

Human expert evaluations favor the health-grounded synthetic users over generic ones.

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.