# The Anatomy of a Personal Health Agent

arXiv: https://arxiv.org/abs/2508.20148 · HTML: https://mlsanity.com/paper/2508.20148/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2025.

## Built on by (most cited first, 18 of 18)

- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [Towards a General Intelligence and Interface for Wearable Health Data](https://mlsanity.com/paper/2605.22759/) (2026)
- [SynthWorlds: Controlled Parallel Worlds for Disentangling Reasoning and Knowledge in Language Models](https://mlsanity.com/paper/2510.24427/) (2025)
- [Medical Reasoning with Large Language Models: A Survey and MR-Bench](https://mlsanity.com/paper/2604.08559/) (2026)
- [RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills](https://mlsanity.com/paper/2606.18203/) (2026)
- [Use of Continuous Glucose Monitoring with Machine Learning to Identify Metabolic Subphenotypes and Inform Precision Lifestyle Changes](https://mlsanity.com/paper/2511.03986/) (2025)
- [How Well Do Multimodal Models Reason on ECG Signals?](https://mlsanity.com/paper/2603.00312/) (2026)
- [WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning](https://mlsanity.com/paper/2606.18147/) (2026)
- [OpenMHC: Accelerating the Science of Wearable Foundation Models](https://mlsanity.com/paper/2607.16235/) (2026)
- [Personal Care Utility (PCU): Building the Health Infrastructure for Everyday Insight and Guidance](https://mlsanity.com/paper/2510.22602/) (2025)
- [An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data](https://mlsanity.com/paper/2604.14615/) (2026)
- [Rethinking Health Agents: From Siloed AI to Collaborative Decision Mediators](https://mlsanity.com/paper/2603.24986/) (2026)
- [The Cost of Language: Centroid Erasure Exposes and Exploits Modal Competition in Multimodal Language Models](https://mlsanity.com/paper/2604.14363/) (2026)
- [Artificial intelligence language technologies in multilingual healthcare: Grand challenges ahead](https://mlsanity.com/paper/2605.01441/) (2026)
- [Personal Care Utility: Health as Everyday Infrastructure](https://mlsanity.com/paper/2606.14145/) (2026)
- [Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training](https://mlsanity.com/paper/2607.02118/) (2026)
- [BALMS: Benchmarking Agentic LLMs for Longitudinal Mental Health Sensing](https://mlsanity.com/paper/2608.27219/) (2026)
- [A Task-Oriented Multi-Agent Framework for Complex Wearable Health Analysis](https://mlsanity.com/paper/2609.24107/) (2026)

## Abstract (arXiv)

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.