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

arXiv: https://arxiv.org/abs/2604.02665 · HTML: https://mlsanity.com/paper/2604.02665/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 43 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 10 of 10)

- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Process-Centric Analysis of Agentic Software Systems](https://mlsanity.com/paper/2512.02393/) (2025)
- [RefDiff: Detecting Refactorings in Version Histories](https://mlsanity.com/paper/1704.01544/) (2017)
- [Evaluating SZZ Implementations Through a Developer-informed Oracle](https://mlsanity.com/paper/2102.03300/) (2021)

## Built on by (most cited first, 2 of 2)

- [Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic Tasks](https://mlsanity.com/paper/2608.03222/) (2026)
- [How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Study](https://mlsanity.com/paper/2607.10856/) (2026)

## Abstract (arXiv)

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.