Papers
arxiv:2604.02665

AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits

Published on Apr 3
Authors:
,
,
,
,
,
,
,
,
,

Abstract

The SZZ algorithm is the dominant technique for identifying bug-inducing commits and underpins many software engineering tasks, such as defect prediction and vulnerability analysis. Despite numerous variants, including recent LLM-based approaches, performance remains limited on developer-annotated datasets (e.g., recall of 0.552 on the Linux kernel). A key limitation is the reliance on git blame, which traces line-level changes within the same file, failing in common scenarios such as ghost and cross-file cases-making nearly one-quarter of bug-inducing commits inherently untraceable. Moreover, current approaches follow fixed pipelines that restrict iterative reasoning and exploration, unlike developers who investigate bugs through an interactive, multi-tool process. To address these challenges, we propose AgentSZZ, an agent-based framework that leverages LLM-driven agents to explore repositories and identify bug-inducing commits. Unlike prior methods, AgentSZZ integrates task-specific tools, domain knowledge, and a ReAct-style loop to enable adaptive and causal tracing of bugs. A structured compression module further improves efficiency by reducing redundant context while preserving key evidence. Extensive experiments on three widely used datasets show that AgentSZZ consistently outperforms state-of-the-art SZZ algorithms across all settings, achieving F1-score gains of up to 27.2% over prior LLM-based approaches. The improvements are especially pronounced in challenging scenarios such as cross-file and ghost commits, with recall gains of up to 300% and 60%, respectively. Ablation studies show that task-specific tools and domain knowledge are critical, while compression tool outputs reduce token consumption by over 30% with negligible impact. The replication package is available.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2604.02665
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2604.02665 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2604.02665 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2604.02665 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.