发表机构
University of Washington; Delft University of Technology; Xiamen University（华盛顿大学; 代尔夫特理工大学; 厦门大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对生物医学图像分析中分布变化阻碍模型部署的问题，提出OPERA多智能体集成框架，通过离线策略学习专家权重分配，结合多种机制协调智能体，经多数据集评估，有效提升性能与校准质量，为可部署生物医学AI提供实用路径。
AI 中文摘要
生物医学图像分析跨越多种模式和任务，但现实世界中的部署受到扫描仪、协议和患者群体间严重分布变化的阻碍。高性能模型需要反复进行特定领域的微调，在标签稀缺或隐私限制数据共享时成本过高且不切实际。我们提出OPERA（离线策略引导专家路由与适应），这是一个多智能体集成框架，通过将专家权重分配视为离线策略学习问题来解决部署瓶颈。从少量验证集学习路由策略，无需对任何专家智能体进行梯度更新，然后在测试时进行适应以处理分布变化。OPERA通过互补机制协调异构专家智能体。专家分析模块离线学习选择策略，每个智能体通过温度调整进行置信度校准，还纳入分布感知适应，通过未标记测试数据的统计信息动态调整类权重。实例级路由利用模型间一致性和预测熵将每个样本分配给最合适的专家。我们在9个数据集上评估OPERA，与30多个基线进行比较，结果表明离线策略引导的专家智能体协调是无需重新训练即可部署生物医学人工智能的实用途径。代码在GitHub上。
英文摘要
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 \href{https://github.com/HUANGLIZI/OPERA}{GitHub}.
CommentsAccepted by ACM MM 2026. 18 pages
