Newest papers

A Multi-Agent Framework for Automated Machine Learning with Evidence-based Planning for Medical Image Analysis

Yiqing Shen, Mathias Unberath · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28410 · cited by 0 works (OpenAlex) · open-access PDF

French

L'apprentissage profond est devenu l'outil par défaut pour l'analyse d'images médicales, alimenté par le mouvement open-source. Cependant, atteindre les meilleures performances sur une tâche donnée reste difficile, avec la sélection d'architecture et l'optimisation hyperparamétrique (HPO) toujours considéré comme "plus d'art qu'une science". L'apprentissage automatique de machine (AutoML) automatise des parties de la formation des modèles, mais aide peu dans l'imagerie médicale: les approches à usage général manquent d'architectures médicales et de pré-traitement, et celles axées sur la médecine nécessitent une expertise en ingénierie et restent limitées à des tâches étroites telles

Machine translation (Meta M2M100); the English original follows.

Abstract

Deep learning has become the default tool for medical image analysis, driven by the open-source movement. However, achieving the best performance on a given task remains difficult, with architecture selection and hyperparameter optimization (HPO) still considered "more of an art than a science". Automated machine learning (AutoML) automates parts of model training, yet helps little in medical imaging: general-purpose approaches lack medical architectures and preprocessing, and medical-focused ones demand engineering expertise and remain confined to narrow tasks such as 3D segmentation. We introduce MedicalMLOmni, a multi-agent AutoML framework that automates model training for diverse single- and multi-modal medical tasks through a natural language interface. Specifically, MedicalMLOmni performs evidence-based planning by retrieving published results to guide model selection and configuration, and employs parallel HPO where multiple agents explore adjustment strategies concurrently. MedicalMLOmni achieves the best score on 19 of 20 benchmarks; PMC-VQA is the exception, where a vision-language model with broader pre-training leads. Backbone-matched controls attribute the gains to the framework, not the backbone. By removing coding requirements, MedicalMLOmni lowers the barrier for domain experts with rich datasets but limited engineering expertise.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Artificial intelligence, Machine learning, Task (project management), Hyperparameter, Domain (mathematical analysis)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange