标题： AT-CXR：胸部X光片的不确定性感知代理分诊 显示英文标题

标题： AT-CXR: Uncertainty-Aware Agentic Triage for Chest X-rays

摘要： 代理型人工智能正在迅速发展，但真正的自主医学影像分诊，即在实际约束下系统决定何时停止、升级或推迟的情况，仍相对研究不足。 为解决这一问题，我们引入了AT-CXR，这是一种针对胸部X光的不确定性感知代理。 该系统估计每张病例的置信度和分布拟合，然后遵循逐步策略发出自动决策或放弃，并建议标签供人工干预。 我们评估了两种共享相同输入和动作的路由器设计：一种是确定性规则基础的路由器，另一种是由大型语言模型决定的路由器。 在NIH ChestX-ray14数据集的一个平衡子集上的五折评估中，两种变体都优于强大的零样本视觉-语言模型和最先进的监督分类器，在全覆盖率准确性方面表现更好，并且在选择性预测性能方面表现出色，这由风险-覆盖率曲线下的面积（AURC）较低和高覆盖率下的错误率较低得到证明，同时运行延迟较低，满足实际临床约束。 这两种路由器提供了互补的操作点，使部署能够优先考虑最大吞吐量或最大准确性。 我们的代码可在https://github.com/XLIAaron/uncertainty-aware-cxr-agent获取。 显示英文摘要

摘要： Agentic AI is advancing rapidly, yet truly autonomous medical-imaging triage, where a system decides when to stop, escalate, or defer under real constraints, remains relatively underexplored. To address this gap, we introduce AT-CXR, an uncertainty-aware agent for chest X-rays. The system estimates per-case confidence and distributional fit, then follows a stepwise policy to issue an automated decision or abstain with a suggested label for human intervention. We evaluate two router designs that share the same inputs and actions: a deterministic rule-based router and an LLM-decided router. Across five-fold evaluation on a balanced subset of NIH ChestX-ray14 dataset, both variants outperform strong zero-shot vision-language models and state-of-the-art supervised classifiers, achieving higher full-coverage accuracy and superior selective-prediction performance, evidenced by a lower area under the risk-coverage curve (AURC) and a lower error rate at high coverage, while operating with lower latency that meets practical clinical constraints. The two routers provide complementary operating points, enabling deployments to prioritize maximal throughput or maximal accuracy. Our code is available at https://github.com/XLIAaron/uncertainty-aware-cxr-agent.