mlsanityData to 14 Oct 2026

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

arXiv 2602.13921 ↗First posted 14 Feb 2026cs.LG cs.AI cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 66 references that are in the map. First posted on arXiv 14 Feb 2026.

Builds on

35 of 66 references.

References · 35

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  8. 2017Billion-scale similarity search with GPUscited by 2,497
  9. 2016Understanding intermediate layers using linear classifier probescited by 1,353
  10. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,310
  11. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  12. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
23 more
  1. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
  2. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 609
  3. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 421
  4. 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 361
  5. 2023RepoBench: Benchmarking Repository-Level Code Auto-Completion Systemscited by 353
  6. 2017Residual Gated Graph ConvNetscited by 346
  7. 2024SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?cited by 203
  8. 2025Multi-SWE-bench: A Multilingual Benchmark for Issue Resolvingcited by 171
  9. 2025Qwen2.5-1M Technical Reportcited by 164
  10. 2024RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graphcited by 91
  11. 2025LocAgent: Graph-Guided LLM Agents for Code Localizationcited by 86
  12. 2025SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agentscited by 85
  13. 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databasescited by 65
  14. 2025OrcaLoca: An LLM Agent Framework for Software Issue Localizationcited by 45
  15. 2024CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Rerankingcited by 37
  16. 2023Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Modelscited by 35
  17. 2024SWE-bench-java: A GitHub Issue Resolving Benchmark for Javacited by 34
  18. 2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Taskscited by 27
  19. 2025SweRank: Software Issue Localization with Code Rankingcited by 20
  20. 2020BuGL -- A Cross-Language Dataset for Bug Localizationcited by 2
  21. 2020DRAST -- A Deep Learning and AST Based Approach for Bug Localizationcited by 1
  22. 2021BLESER: Bug Localization Based on Enhanced Semantic Retrievalcited by 1
  23. 2025OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Predictioncited by 1

Built on by

Not cited yet.