OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis

Hugging Face Daily Papers Papers
biomedical-image-analysis multi-agent-ensemble offline-policy-learning test-time-adaptation distribution-shift expert-routing domain-generalization

Summary

OPERA proposes a multi-agent ensemble framework that treats expert weight assignment as an offline policy learning problem for universal biomedical image analysis, enabling test-time adaptation without retraining and consistently improving performance across 9 datasets and 30+ baselines.

Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, protocols, and patient populations. High-performing models consequently require repeated domain-specific fine-tuning, which is a costly cycle that becomes impractical when labels are scarce or privacy constraints limit data sharing. We propose OPERA (Offline Policy-guided Expert Routing and Adaptation), a multi-agent ensemble framework that addresses this deployment bottleneck by treating expert weight assignment as an offline policy learning problem: a routing policy is learned from a small validation set without gradient updates to any expert agent, then deployed with test-time adaptation to handle distribution shift. OPERA coordinates heterogeneous specialist agents through complementary mechanisms. The expert profiling module learns selection policies offline, enabling informed allocation of expertise. Each agent undergoes confidence calibration through temperature adjustment, ensuring more reliable probabilistic outputs. OPERA also incorporates distribution aware adaptation, where class weights are dynamically adjusted at the batch level using statistics derived from unlabeled test data. Instance level routing assigns each sample to the most suitable expert by leveraging inter model agreement and predictive entropy. We evaluate OPERA on 9 datasets covering fundus photography, chest X-ray, CT, MRI, and multimodal diagnostic benchmarks, comparing against 30+ baselines across classification, segmentation, and multimodal settings. OPERA consistently improves performance and calibration quality, demonstrating that offline policy-guided expert agents coordination is a practical path to deployable biomedical AI without retraining. Code is on https://github.com/HUANGLIZI/OPERA{GitHub}.
Original Article
View Cached Full Text

Cached at: 07/29/26, 07:54 PM

Paper page - OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis

Source: https://huggingface.co/papers/2607.25108

Abstract

Biomedicalimageanalysisspansdiversemodalitiesandtasks,yetreal-worlddeploymentishinderedbyseveredistributionshiftsacrossscanners,protocols,andpatientpopulations.High-performingmodelsconsequentlyrequirerepeateddomain-specificfine-tuning,whichisacostlycyclethatbecomesimpracticalwhenlabelsarescarceorprivacyconstraintslimitdatasharing.WeproposeOPERA(OfflinePolicy-guidedExpertRoutingandAdaptation),amulti-agentensembleframeworkthataddressesthisdeploymentbottleneckbytreatingexpertweightassignmentasanofflinepolicylearningproblem:aroutingpolicyislearnedfromasmallvalidationsetwithoutgradientupdatestoanyexpertagent,thendeployedwithtest-timeadaptationtohandledistributionshift.OPERAcoordinatesheterogeneousspecialistagentsthroughcomplementarymechanisms.Theexpertprofilingmodulelearnsselectionpoliciesoffline,enablinginformedallocationofexpertise.Eachagentundergoesconfidencecalibrationthroughtemperatureadjustment,ensuringmorereliableprobabilisticoutputs.OPERAalsoincorporatesdistributionawareadaptation,whereclassweightsaredynamicallyadjustedatthebatchlevelusingstatisticsderivedfromunlabeledtestdata.Instancelevelroutingassignseachsampletothemostsuitableexpertbyleveragingintermodelagreementandpredictiveentropy.WeevaluateOPERAon9datasetscoveringfundusphotography,chestX-ray,CT,MRI,andmultimodaldiagnosticbenchmarks,comparingagainst30+baselinesacrossclassification,segmentation,andmultimodalsettings.OPERAconsistentlyimprovesperformanceandcalibrationquality,demonstratingthatofflinepolicy-guidedexpertagentscoordinationisapracticalpathtodeployablebiomedicalAIwithoutretraining.Codeisonhttps://github.com/HUANGLIZI/OPERA{GitHub}.

View arXiv pageView PDFProject pageGitHub1Add to collection

Get this paper in your agent:

hf papers read 2607\.25108

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/2607.25108 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.25108 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.25108 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

Opera: A Verbal Critic Framework for Long-horizon Coding Agents

Hugging Face Daily Papers

Opera is a verbal critic framework for long-horizon coding agents that treats each correction as a persistent note, tracking agent actions to distinguish mere compliance from actual resolution. It improves resolver rates by up to 15 percentage points across benchmarks and provides on-policy training data that boosts Qwen3.5-9B's SWE-Bench Pro performance without needing a critic at inference time.