AgenticSZZ: Temporal Knowledge Graph-Guided Agentic Bug-Inducing Commit Identification
Yu Shi, Hao Li, Bram Adams, Ahmed E. Hassan

TL;DR
AgenticSZZ introduces a novel approach using Temporal Knowledge Graphs and LLMs to improve bug-inducing commit identification beyond traditional blame-based methods, significantly enhancing accuracy.
Contribution
This paper pioneers the application of Temporal Knowledge Graphs and LLM-driven graph search for more effective bug-inducing commit detection in software evolution.
Findings
AgenticSZZ achieves F1-scores up to 0.79, outperforming state-of-the-art by 34%.
Both TKG and agent components significantly contribute to bug detection performance.
Effective TKG navigation depends on sufficiently capable LLMs, amplifying the benefits of the architecture.
Abstract
Identifying Bug-Inducing Commits (BICs) is fundamental for understanding software defects and enabling downstream tasks such as defect prediction and automated program repair. Yet existing SZZ-based approaches rely on git blame, restricting the search space to commits that directly modified the fixed lines. Our preliminary study on 2,102 validated bug-fixing commits reveals this limitation is significant: 28% of BICs require traversing commit history beyond blame results and 14% are blameless. We present AgenticSZZ, the first approach to apply Temporal Knowledge Graphs (TKGs) to software evolution analysis. AgenticSZZ reframes BIC identification from ranking blame commits into a graph search problem, where temporal ordering is fundamental to causal reasoning about bug introduction. The approach operates in two phases: (1) constructing a TKG that encodes commits with temporal and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
