# AutoHealth: An Uncertainty-Aware Multi-Agent System for Autonomous Health Data Modeling

arXiv: https://arxiv.org/abs/2602.01078 · HTML: https://mlsanity.com/paper/2602.01078/

## 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 5 of its 23 references that are in the map.
- First posted on arXiv 1 Feb 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, 5 of 5)

- [DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?](https://mlsanity.com/paper/2409.07703/) (2024)
- [AutoML-GPT: Automatic Machine Learning with GPT](https://mlsanity.com/paper/2305.02499/) (2023)
- [Large Language Model-based Data Science Agent: A Survey](https://mlsanity.com/paper/2508.02744/) (2025)
- [SymbolicAI: A framework for logic-based approaches combining generative models and solvers](https://mlsanity.com/paper/2402.00854/) (2024)
- [OpenLens AI: Fully Autonomous Research Agent for Health Infomatics](https://mlsanity.com/paper/2509.14778/) (2025)

## Abstract (arXiv)

LLM-based agents have demonstrated strong potential for autonomous machine learning, yet their applicability to health data remains limited. Existing systems often struggle to generalize across heterogeneous health data modalities, rely heavily on predefined solution templates with insufficient adaptation to task-specific objectives, and largely overlook uncertainty estimation, which is essential for reliable decision-making in healthcare. To address these challenges, we propose textitAutoHealth, a novel uncertainty-aware multi-agent system that autonomously models health data and assesses model reliability. textitAutoHealth employs closed-loop coordination among five specialized agents to perform data exploration, task-conditioned model construction, training, and optimization, while jointly prioritizing predictive performance and uncertainty quantification. Beyond producing ready-to-use models, the system generates comprehensive reports to support trustworthy interpretation and risk-aware decision-making. To rigorously evaluate its effectiveness, we curate a challenging real-world benchmark comprising 17 tasks across diverse data modalities and learning settings. textitAutoHealth completes all tasks and outperforms state-of-the-art baselines by 29.2% in prediction performance and 50.2% in uncertainty estimation.