针对药物问答的虚假信息问题，提出基于权威源的智能代理与评测基准。
DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question Answering
- 构建多智能体系统，通过反射式工作流检索原始药监数据
- 在3772项评测中实现91.8%的权威源引用率，优于次优模型10.1个百分点
- 提供可信赖的评测标准，适合医疗AI验证与临床决策支持研究
药物信息问答属于高风险场景，幻觉信息可能误导临床决策，且每个引用事实的来源可靠性同样重要。我们提出DrugClaw，一种基于多智能体的检索增强系统，通过反射驱动的状态机工作流查询药物与药警技能注册库，并返回基于原始监管或同行评审文献的答案。同时，我们构建了DrugAudit，一个包含3,772个样本的权威感知评测集，采用双评委大模型评分协议，评估上游来源匹配度、语义片段重叠及引用忠实性，评委间一致性kappa=0.88（几乎完美）。在DrugAudit及MedQA（751项）、PubMedQA（512项）的药物相关子集上，DrugClaw在各项指标中均排名第一：复合证据指数（双评委）、经评委评估的答案正确率、原始来源引用率（0.918，较次优提升10.1个百分点）、忠实性（0.887，提升5.9个百分点）、MedQA（0.920）、PubMedQA（0.693）。
原文摘要 · Abstract (English)
Drug-information question answering is a high-stakes setting where hallucinated facts can mislead clinical decision-making and the provenance of each cited fact matters as much as the fact itself. We present DrugClaw, a multi-agent retrieval-augmented system that queries a registry of drug and pharmacovigilance skills via a reflection-driven state-machine workflow and returns answers grounded in primary regulatory or peer-reviewed records. We also contribute DrugAudit, a 3,772-item authority-aware benchmark with an evaluation panel that scores upstream-of-gold source match, token-level semantic snippet overlap, and citation faithfulness under a dual-judge LLM-as-judge protocol with inter-judge kappa = 0.88 (almost-perfect). Across DrugAudit plus drug-related subsets of MedQA (751) and PubMedQA (512), DrugClaw is top-1 on every column of the headline table: composite Evidence Index under both judges, judge-mediated answer correctness, primary-source rate (0.918, +10.1 pp over next-best), faithfulness (0.887, +5.9 pp), MedQA (0.920), and PubMedQA (0.693).
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。