一句话：提出基于LLM智能体的工作流，通过提取可grep模式搜索候选提交，大幅提升引入缺陷提交识别F1。
从修复提交中识别引入缺陷的提交（bug-introducing commits）是软件仓库挖掘中的经典问题，SZZ 方法自2005年提出后影响深远，但二十年来在 Linux 内核数据集上的最佳 F1 提升有限。本文提出一种简单的 LLM 智能体工作流：在候选提交集合中搜索，并让智能体从修复提交的 diff 和消息中提取简短、可 grep 的模式，用于高效检索真正引入缺陷的提交。在常用的 Linux 内核数据集上，该方法将 F1 从 0.64 提升到 0.81，提升幅度超过原始 2005 年方法（0.54）到此前 SOTA（0.64）的差距。作者进一步分析了智能体成功的原因，并讨论了这些发现对根因理解与修复的启示。
Śliwerski, Zimmermann, and Zeller (SZZ) just won the 2026 ACM SIGSOFT Impact Award for asking: When do changes induce fixes? Their paper from 2005 served as the foundation for a wide array of approaches aimed at identifying bug-introducing changes (or commits) from fix commits in software repositories. But even after two decades of progress, the best-performing approach from 2025 yields a modest increase of 10 percentage points in F1-score on the most popular Linux kernel dataset. In this paper, we uncover how and why LLM-based agents can substantially advance the state-of-the-art in identifying bug-introducing commits from fix commits. We propose a simple agentic workflow based on searching a set of candidate commits and find that it raises the F1-score from 0.64 to 0.81 on the most popular Linux kernel dataset, a bigger jump than between the original 2005 method (0.54) and the previous SOTA (0.64). We also uncover why agents are so successful: They derive short greppable patterns from the fix commit diff and message and use them to effectively search and find bug-introducing commits in large candidate sets. Finally, we also discuss how these insights might enable further progress in root cause understanding and repair.