# SLICEMATE: Accurate and Scalable Static Program Slicing via LLM-Powered Agents

arXiv: https://arxiv.org/abs/2507.18957 · HTML: https://mlsanity.com/paper/2507.18957/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 58 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [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)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [GraphCodeBERT: Pre-training Code Representations with Data Flow](https://mlsanity.com/paper/2009.08366/) (2020)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks](https://mlsanity.com/paper/2105.12655/) (2021)
- [Software Testing with Large Language Models: Survey, Landscape, and Vision](https://mlsanity.com/paper/2307.07221/) (2023)
- [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024)
- [Large Language Models for Test-Free Fault Localization](https://mlsanity.com/paper/2310.01726/) (2023)
- [You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects](https://mlsanity.com/paper/2412.10133/) (2024)
- [SourcererCC: Scaling Code Clone Detection to Big Code](https://mlsanity.com/paper/1512.06448/) (2015)
- [BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studies](https://mlsanity.com/paper/2401.15481/) (2024)
- [Bridging Bug Localization and Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models](https://mlsanity.com/paper/2502.15292/) (2025)
- [Locating Faults with Program Slicing: An Empirical Analysis](https://mlsanity.com/paper/2101.03008/) (2021)
- [IncBL: Incremental Bug Localization](https://mlsanity.com/paper/2106.07413/) (2021)
- [Utilizing Precise and Complete Code Context to Guide LLM in Automatic False Positive Mitigation](https://mlsanity.com/paper/2411.03079/) (2024)
- [The Impact of Program Reduction on Automated Program Repair](https://mlsanity.com/paper/2408.01134/) (2024)

## Abstract (arXiv)

Static program slicing, which extracts the executable portions of a program that affect the values at a specific location, supports many software analysis tasks such as debugging and security auditing. However, traditional slicing tools rely on computationally expensive reachability analysis over dependency graphs, which struggle to scale to large programs and often fail to handle code with incomplete syntax. Recently emerged learning-based methods, while more robust to such cases, still fall short of achieving comparable performance to traditional methods on well-formed code. In this work, we propose SliceMate, a novel static program slicing solution powered by Large Language Model (LLM) agents. It bypasses the need for explicit dependency graph construction and achieving superior slicing accuracy. Concretely, SliceMate integrates three specialized agents: (1) a synthesis agent that produces candidate slices by incrementally expanding the scan scope across functions and files guided by LLM-inferred dependencies; (2) a verification agent that performs conciseness and completeness checks of the candidate slices, detecting missing or irrelevant statements; and (3) a refinement agent that repairs the slices with minimal edits in accordance with the verification results. These agents are orchestrated by a control module that ensures timely convergence and outputs high-quality slices without manual intervention. For rigorous evaluation, we construct a new and high-quality benchmark, SliceBench, comprising 2,200 manually annotated Java and Python programs, with program lengths ranging from 5 to 8,577 lines, significantly larger than those in existing slicing benchmarks. Experimental results show that SliceMate greatly outperforms both traditional and learning-based slicing tools.