ChatPPG.
Join free
First page or project page of “The anatomy of a personal health agent” (opens in a new tab)

PaperarXiv:2508.20148

The anatomy of a personal health agent

Preprint2026Added Oct 22, 2026

  • AH
  • KG
  • VS
  • HY
  • AP
  • ZZ
  • YZ
  • QH
  • +32

Authors: A. Ali Heydari, Ken Gu, Vidya Srinivas, Hong Yu, Akshay Paruchuri, Zhihan Zhang, Yuwei Zhang, Qian He, Hamid Palangi, Nova Hammerquist,

+30 moreAhmed A. Metwally, Brent Winslow, Yubin Kim, Kumar Ayush, Yuzhe Yang, Girish Narayanswamy, Maxwell A. Xu, Jake Garrison, Samuel Schmidgall, Amy Armento Lee, Jenny Vafeiadou, Ben Graef, Isaac R. Galatzer-Levy, Erik Schenck, Andrew Barakat, Javier Perez, Jacqueline Shreibati, John Hernandez, Anthony Z. Faranesh, Naghmeh Rezaei, Javier L. Prieto, Conor Heneghan, Jiening Zhan, Mark Malhotra, Shwetak Patel, Yun Liu, Tim Althoff, Xin Liu, Daniel McDuff, Xuhai Orson Xu

Nature, published 2026-10-21 (preprint arXiv 2508.20148, 2025-08-27)

PDF (opens in a new tab) arXiv2508.20148 (opens in a new tab) Publisher (opens in a new tab) Cite

Open code

First page or project page of “The anatomy of a personal health agent” (opens in a new tab)

Heydari, A. Ali et al., "The Anatomy of a Personal Health Agent", arXiv:2508.20148, CC BY 4.0

TL;DR

Multi-agent personal health agent (PHA) reasoning over consumer wearable data and medical records. Four user journeys (general knowledge, personal data interpretation, wellness advice, symptom assessment) → three sub-agents: data science (longitudinal wearable + medical data with population statistics), health domain expert, health coach (multi-turn goals, psychological strategies). 11 benchmark tasks, >7,000 annotations and ~1,350 h of expert and end-user evaluation. Open-sourced orchestrator, sub-agents, prompts, tool scaffolding and sandboxed code execution; model-agnostic.

  • Form factor: wrist

Abstract

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.

Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Signals

PPGIMU

Keywords

LLM-agentmulti-agentpersonal-healthhealth-coachdata-science-agentwearablesbenchmarkhuman-evaluationGoogleGeminiNature

How it works

How Method works: Setup → Method → TargetSetup: Signals (ppg, imu); Form factor (wrist). Method: Method (Language-aligned).SetupSignals: ppg, imuSignalsppg, imuForm factor: wristForm factorwristMethodMethodLanguage-aligned

Cite this paper

APA

Heydari, A. A., Gu, K., Srinivas, V., Yu, H., Paruchuri, A., Zhang, Z., Zhang, Y., He, Q., Palangi, H., Hammerquist, N., Metwally, A. A., Winslow, B., Kim, Y., Ayush, K., Yang, Y., Narayanswamy, G., Xu, M. A., Garrison, J., Schmidgall, S., . . . Xu, X. O. (2026). The anatomy of a personal health agent. Nature. https://doi.org/10.1038/s41586-026-11161-8

BibTeX

@article{heydari2026anatomy,
  title         = {{The anatomy of a personal health agent}},
  author        = {Heydari, A. Ali and Gu, Ken and Srinivas, Vidya and Yu, Hong and Paruchuri, Akshay and Zhang, Zhihan and Zhang, Yuwei and He, Qian and Palangi, Hamid and Hammerquist, Nova and Metwally, Ahmed A. and Winslow, Brent and Kim, Yubin and Ayush, Kumar and Yang, Yuzhe and Narayanswamy, Girish and Xu, Maxwell A. and Garrison, Jake and Schmidgall, Samuel and Lee, Amy Armento and Vafeiadou, Jenny and Graef, Ben and Galatzer-Levy, Isaac R. and Schenck, Erik and Barakat, Andrew and Perez, Javier and Shreibati, Jacqueline and Hernandez, John and Faranesh, Anthony Z. and Rezaei, Naghmeh and Prieto, Javier L. and Heneghan, Conor and Zhan, Jiening and Malhotra, Mark and Patel, Shwetak and Liu, Yun and Althoff, Tim and Liu, Xin and McDuff, Daniel and Xu, Xuhai Orson},
  year          = {2026},
  journal       = {Nature},
  doi           = {10.1038/s41586-026-11161-8},
  eprint        = {2508.20148},
  archivePrefix = {arXiv}
}

Built from the hub record. Check it against the publisher before submitting.

Added to the ChatPPG research hub

Same tasks, data and authors

Papers

Models