PatchHolmes：基于列表选择的智能体补丁检索
原标题：PatchHolmes: Agentic Patch Retrieval via Listwise Selection
AI 摘要
该论文提出 PatchHolmes，一个两阶段补丁检索系统，用于为已知漏洞找到修复提交。第一阶段使用混合检索器，第二阶段采用智能体循环，一次性读取前100个候选列表并选择性阅读3到10个提交，最终提交最佳结果。在 GitHubAD 数据集上，PatchHolmes 的 Recall@1 比逐点分类器 Favia 高 25.34%，比 IRCoT 高 31.40%，且每个 CVE 仅需一次智能体对话。系统基于冻结的开源权重模型和本地 Git 仓库运行，无需微调或外部搜索 API。
正文节选
PatchHolmes: Agentic Patch Retrieval via Listwise SelectionThanks: Accepted at AACL-IJCNLP 2026. This is the authors’ preprint version. Abstract Patch retrieval, the task of finding the commit that fixes a known vulnerability, is the foundation of vulnerability management workflows, yet 60% to 63% of CVEs in the major advisory databases lack a patch link. We present PatchHolmes, a two-phase patch retrieval system that pairs a hybrid first-stage retriever with an agentic second-stage inspection l