Paper

The Anatomy of a Personal Health Agent

A Ali Heydari, Hammerquist, Nova, Barakat, Andrew, Palangi, Hamid, Faranesh, Anthony Z, Metwally, Ahmed A, Graef, Ben, Gu, Ken, Vafeiadou, Jenny, Paruchuri, Akshay, Kumar Ayush, Hernandez, John, Heneghan, Connor, Perez, Javier, Zhan, Jiening, He, Qian, Xu, Maxwell A, Prieto, Javier L, Zhang, Yuwei, Althoff, Tim, Yang, Yuzhe, Amy Armento Lee, Malhotra, Mark, Yu, Hong, Winslow, Brent, Garrison, Jake, Galatzer-Levy, Isaac R, Schenck, Erik, Liu, Yun, Xuhai "Orson" Xu, Zhang, Zhihan, Narayanswamy, Girish, Patel, Shwetak, Srinivas, Vidya, Kim, Yubin, McDuff, Daniel, Liu, Xin, Shreibati, Jacqueline

2025

Overview

Health is a fundamental pillar of human wellness, and the rapid advancements in large language models (LLMs) have driven the development of a new generation of health agents. However, the application of health agents to fulfill the diverse needs of individuals in daily non-clinical settings is underexplored. In this work, we aim to build a comprehensive personal health agent that is able to reason about multimodal data from everyday consumer wellness devices and common personal health records, and provide personalized health recommendations. To understand end-users' needs when interacting with such an assistant, we conducted an in-depth analysis of web search and health forum queries, alongside qualitative insights from users and health experts gathered through a user-centered design process. Based on these findings, we identified three major categories of consumer health needs, each of which is supported by a specialist sub-agent: (1) a data science agent that analyzes personal time-series wearable and health record data, (2) a health domain expert agent that integrates users' health and contextual data to generate accurate, personalized insights, and (3) a health coach agent that synthesizes data insights, guiding users using a specified psychological strategy and tracking users' progress. Furthermore, we propose and develop the Personal Health Agent (PHA), a multi-agent framework that enables dynamic, personalized interactions to address individual health needs. To evaluate each sub-agent and the multi-agent system, we conducted automated and human evaluations across 10 benchmark tasks, involving more than 7,000 annotations and 1,100 hours of effort from health experts and end-users. Our work represents the most comprehensive evaluation of a health agent to date and establishes a strong foundation towards the futuristic vision of a personal health agent accessible to everyone.

• Publisher: Cornell University Library, arXiv.org
• Subject: Annotations / Customization / Data science / Large language models / Multiagent systems / Personal health / Qualitative analysis