GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Juntong, Chen, Libin, Wang, Xiyuan, Kang, Shijia, Yang, Haotong, Zheng, Da, Zhang, Muhan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917275397783552
author Wang, Juntong
Chen, Libin
Wang, Xiyuan
Kang, Shijia
Yang, Haotong
Zheng, Da
Zhang, Muhan
author_facet Wang, Juntong
Chen, Libin
Wang, Xiyuan
Kang, Shijia
Yang, Haotong
Zheng, Da
Zhang, Muhan
contents Repository-level bug localization-the task of identifying where code must be modified to fix a bug-is a critical software engineering challenge. Standard Large Language Modles (LLMs) are often unsuitable for this task due to context window limitations that prevent them from processing entire code repositories. As a result, various retrieval methods are commonly used, including keyword matching, text similarity, and simple graph-based heuristics such as Breadth-First Search. Graph Neural Networks (GNNs) offer a promising alternative due to their ability to model complex, repository-wide dependencies; however, their application has been hindered by the lack of a dedicated benchmark. To address this gap, we introduce GREPO, the first GNN benchmark for repository-scale bug localization tasks. GREPO comprises 86 Python repositories and 47294 bug-fixing tasks, providing graph-based data structures ready for direct GNN processing. Our evaluation of various GNN architectures shows outstanding performance compared to established information retrieval baselines. This work highlights the potential of GNNs for bug localization and established GREPO as a foundation resource for future research, The code is available at https://github.com/qingpingmo/GREPO.
format Preprint
id arxiv_https___arxiv_org_abs_2602_13921
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization
Wang, Juntong
Chen, Libin
Wang, Xiyuan
Kang, Shijia
Yang, Haotong
Zheng, Da
Zhang, Muhan
Machine Learning
Artificial Intelligence
Software Engineering
Repository-level bug localization-the task of identifying where code must be modified to fix a bug-is a critical software engineering challenge. Standard Large Language Modles (LLMs) are often unsuitable for this task due to context window limitations that prevent them from processing entire code repositories. As a result, various retrieval methods are commonly used, including keyword matching, text similarity, and simple graph-based heuristics such as Breadth-First Search. Graph Neural Networks (GNNs) offer a promising alternative due to their ability to model complex, repository-wide dependencies; however, their application has been hindered by the lack of a dedicated benchmark. To address this gap, we introduce GREPO, the first GNN benchmark for repository-scale bug localization tasks. GREPO comprises 86 Python repositories and 47294 bug-fixing tasks, providing graph-based data structures ready for direct GNN processing. Our evaluation of various GNN architectures shows outstanding performance compared to established information retrieval baselines. This work highlights the potential of GNNs for bug localization and established GREPO as a foundation resource for future research, The code is available at https://github.com/qingpingmo/GREPO.
title GREPO: A Benchmark for Graph Neural Networks on Repository-Level Bug Localization
topic Machine Learning
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2602.13921