让医疗智能体学会从多个专用模型中选对工具，提升诊断准确性。
Picking the Right Specialist: Attentive Neural Process-based Selection of Task-Specialized Models as Tools for Agentic Healthcare Systems
- 用注意力神经过程动态选择最适合当前任务的模型
- 在1448个胸部X光查询上超越10种顶尖方法
- 首个针对医疗代理的专用模型选择基准，适合研究者使用
任务专用模型是医疗智能体的核心，可支持疾病诊断、定位和报告生成等任务。然而，单一最优模型很少存在；不同样本下多个模型表现各异。因此，智能体需从异构模型池中可靠选择合适工具。本文提出ToolSelect，通过最小化采样候选工具的群体风险，学习任务条件下的模型选择策略。具体采用基于查询与模型行为摘要的注意力神经过程选择器。为填补测试空白，首次构建包含17种疾病检测、19种报告生成、6种视觉定位和13种VQA模型的胸部X光代理环境，并开发了包含1448个查询的ToolSelectBench基准。结果表明，ToolSelect在四类任务上持续优于10种现有先进方法。
原文摘要 · Abstract (English)
Task-specialized models form the backbone of agentic healthcare systems, enabling the agents to answer clinical queries across tasks such as disease diagnosis, localization, and report generation. Yet, for a given task, a single "best" model rarely exists. In practice, each task is better served by multiple competing specialist models where different models excel on different data samples. As a result, for any given query, agents must reliably select the right specialist model from a heterogeneous pool of tool candidates. To this end, we introduce ToolSelect, which adaptively learns model selection for tools by minimizing a population risk over sampled specialist tool candidates using a consistent surrogate of the task-conditional selection loss. Concretely, we propose an Attentive Neural Process-based selector conditioned on the query and per-model behavioral summaries to choose among the specialist models. Motivated by the absence of any established testbed, we, for the first time, introduce an agentic Chest X-ray environment equipped with a diverse suite of task-specialized models (17 disease detection, 19 report generation, 6 visual grounding, and 13 VQA) and develop ToolSelectBench, a benchmark of 1448 queries. Our results demonstrate that ToolSelect consistently outperforms 10 SOTA methods across four different task families.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。