# A Task-Oriented Multi-Agent Framework for Complex Wearable Health Analysis

arXiv: https://arxiv.org/abs/2609.24107 · HTML: https://mlsanity.com/paper/2609.24107/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 12 of 12)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration](https://mlsanity.com/paper/2310.02170/) (2023)
- [The Anatomy of a Personal Health Agent](https://mlsanity.com/paper/2508.20148/) (2025)
- [PhysioLLM: Supporting Personalized Health Insights with Wearables and Large Language Models](https://mlsanity.com/paper/2406.19283/) (2024)
- [Large Language Models in the Clinic: A Comprehensive Benchmark](https://mlsanity.com/paper/2405.00716/) (2024)
- [Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health](https://mlsanity.com/paper/2502.13920/) (2025)
- [Structural Textile Pattern Recognition and Processing Based on Hypergraphs](https://mlsanity.com/paper/2103.11271/) (2021)
- [WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning](https://mlsanity.com/paper/2606.18147/) (2026)
- [A Self-Evolving Agent for Longitudinal Personal Health Management](https://mlsanity.com/paper/2607.13940/) (2026)
- [HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices](https://mlsanity.com/paper/2607.21019/) (2026)

## Abstract (arXiv)

Wearable health questions often combine data retrieval, longitudinal analysis, and health advice over structured records. Prompting a single large language model with a complete record and a composite query obscures whether every request is executed and which evidence supports the answer. We propose a task-oriented multi-agent framework that represents a composite query as distinct intents and typed tasks with explicit intra-intent dependencies. Specialized agents execute retrieval, analysis, and advice tasks; isolated intent states preserve request boundaries and evidence relationships before aggregation. We evaluate the framework on a synthetic dataset of 10,000 virtual users with one month of longitudinal wearable records, covering structured data retrieval, multi-intent recognition, and overall response quality. Across 1,500 retrieval questions, the Query Agent achieves 98.3% accuracy, compared with 97.9% for the Direct LLM baseline, while reducing average query-stage token consumption from 6,869 to 3,136. On 180 multi-intent questions, the Manager Agent achieves 100.0% Multi-Intent Coverage and 94.4% Multiset Jaccard Similarity. Under the current synthetic evaluation setting, our method receives higher mean Trustworthiness and Transparency scores on both question categories, whereas Actionability does not improve consistently. These results provide preliminary evidence that explicit task organization can support task-relevant data access and data-grounded longitudinal analysis, while leaving health advice generation and validation on real wearable data as open challenges.