Towards Autonomous and Auditable Medical Imaging Model Development
Summary
Introduces AMID, an autonomous multi-agent framework for medical imaging model development that uses LLM agents to plan, execute, and verify experiments. It outperforms general-purpose MLE systems and approaches human-designed solutions on 20 medical imaging tasks.
View Cached Full Text
Cached at: 07/15/26, 04:22 PM
Paper page - Towards Autonomous and Auditable Medical Imaging Model Development
Source: https://huggingface.co/papers/2607.10522 Authors:
,
,
,
,
,
,
,
,
,
Abstract
Largelanguagemodel(LLM)agentsarebeginningtoautomatemachinelearningengineering(MLE)bycouplingplanning,codeexecution,debugging,andempiricalfeedback.Translatingthiscapabilitytomedicalimagingremainsdifficultbecauseeachtaskimposesmodality-specificexperimentationandstrictrequirementsforvalidationprotocolsandpredictionartifacts.HereweintroduceAMID,anautonomousmulti-agentframeworkformedicalimagingmodeldevelopment.AMIDfirstproposesData-ConditionedMethodPlanning,whichrefinescoarsetask-levelsearchspacesintoexecutable,parallelizablemethodlanesgroundedintask-specificdataanalysisandrunnablemedical-imagingresources.ItthendevelopsVerification-GuidedTwo-StageOptimization,movingfrombroadearlyexplorationofdiversemethodlanestoselectiveexploitationofpromisingcandidateswhileenforcingstrictverificationofvalidationprotocols,metriccomputation,andpredictionartifactsthroughouttheoptimization.Across20medicalimagingchallengetasksspanningdiversemodalitiesandpredictiontypes,AMIDoutperformedevaluatedgeneral-purposeMLEsystemsand,onseveraltasks,approachedormatchedstronghuman-designedchallengesolutions.TheseresultssuggestthatAMIDcanturntask-specificmedicalimagingmodeldevelopmentfrombespokemanualengineeringintoanagenticworkflowforproducinghigh-performingandauditablemodelartifactsacrossheterogeneoustasks.
View arXiv pageView PDFGitHub9Add to collection
Get this paper in your agent:
hf papers read 2607\.10522
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.10522 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.10522 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.10522 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
AutoMedBench: Towards Medical AutoResearch with Agentic AI Models
AutoMedBench is a workflow-aware benchmark for autonomous medical-AI research, evaluating agents across five stages on diverse medical imaging tasks. Stage-level scoring reveals validation as the weakest stage, highlighting the need for reliable verification in agentic workflows.
MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs
This paper introduces MedAction, a framework for training LLMs on active, multi-turn clinical diagnosis by simulating iterative test ordering and hypothesis updates. It presents a new dataset, MedAction-32K, and demonstrates state-of-the-art performance for open-source models on medical benchmarks.
A Multi-Domain Red Teaming Framework for Safety, Robustness, and Fairness Evaluation of Medical Large Language Models
This paper presents a multi-domain red teaming framework for evaluating safety, robustness, and fairness of medical LLMs across 690 clinically grounded scenarios. Results show that high aggregate accuracy can mask critical failures, and hybrid evaluation with clinician oversight is necessary for credible safety assessment.
MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
The paper introduces MedExAgent, a framework that formalizes clinical diagnosis as a Partially Observable Markov Decision Process (POMDP) to handle noisy and incomplete information. It proposes a two-stage training pipeline combining supervised finetuning and reinforcement learning to improve diagnostic accuracy and cost-efficiency in medical LLMs.
IMCBench: A benchmark for multimodal LLMs in Image-grounded Medical Conversations
IMCBench is a new benchmark for evaluating multimodal LLMs on image-grounded medical conversations, pairing clinical images with synthetic patient profiles. Evaluations across safety, accuracy, and uncertainty show that even strong models like Claude Opus 4.6 have safety issues, highlighting the need for multi-dimensional evaluation.