AI 中文总结
本研究提出以指南为神谕（GAO）方法，将美国眼科学会指南转化为训练监督信号，零标注训练出GAO-Triage智能体，大幅提升眼科电话分诊的一致性与紧急案例召回率，且性能优于7个通用系统。
AI 中文摘要
为多轮医疗智能体扩充监督信号难度较大，因为专家对话标注成本高昂，且临床对话受隐私限制。我们提出以指南为神谕（Guideline-as-Oracle, GAO），将美国眼科学会指南汇编成一张70行的操作规则表，并将其作为3000条训练对话的实例级监督的唯一来源，仅保留人工标注用于评估。由于将规则转换为对话本身是一个设计问题，我们梳理了8种构建策略，包括引用行层级分配、单事实边界对、仅元数据修复和标签修复，并对每种策略的证据状态进行了刻画：标注机制、无效、混杂或仅作为整体评估。在该语料库上微调9B主干模型得到GAO-Triage，其与201个案例操作参考的一致性从61.7%提升至74.1%（精确McNemar检验p值为0.0046），紧急案例召回率从9.5%提升至69.0%；在第二个随机种子和患者模拟器上，该提升依然存在。我们测试的7个通用系统均未在两个指标上同时优于GAO-Triage，且GAO-Triage在推理时不需要前沿模型。打乱标签-对话分配会使模型退化为常规模型预测器，表明信号来自指南衍生的分配而非对话表面形式。标签修复与训练后期安全退化的消失相吻合。
英文摘要
Scaling supervision for multi-turn medical agents is difficult because expert dialogue annotation is costly and clinical conversations are privacy-restricted. We introduce Guideline-as-Oracle (GAO), which compiles American Academy of Ophthalmology guidance into a 70-row operational rule table and uses it as the sole source of instance-level supervision for 3,000 training dialogues, reserving human labeling for evaluation. Because converting rules into dialogues is itself a design problem, we catalog eight construction strategies, including cited-row tier assignment, one-fact boundary pairs, metadata-only repair, and label repair, and characterize the evidential status of each: labeling mechanism, null, confounded, or evaluated only as a package. Fine-tuning a 9B backbone on this corpus yields GAO-Triage, improving agreement with a 201-case operational reference from 61.7% to 74.1% (exact McNemar p=0.0046) and emergent-case recall from 9.5% to 69.0%; the gains persist across a second seed and patient simulator. None of the seven general-purpose systems we test dominates GAO-Triage on both metrics, and GAO-Triage requires no frontier model at inference time. Permuting label-dialogue assignments collapses the model to a constant-routine predictor, indicating that the signal lies in guideline-derived assignment rather than dialogue surface form. Label repair coincides with the disappearance of a late-training safety degradation.
