mlsanityData to 7 Oct 2026

A Deep Dive into Large Language Models for Automated Bug Localization and Repair

arXiv 2404.11595 ↗First posted 17 Apr 2024cs.SEcited by 39

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have shown impressive effectiveness in various software engineering tasks, including automated program repair (APR). In this study, we take a deep dive into automated bug fixing utilizing LLMs. In contrast to many deep learning-based APR methods that assume known bug locations, rely on line-level localization tools, or address bug prediction and fixing in one step, our approach uniquely employs LLMs to predict bug location at the token level and subsequently utilizes them for bug fixing. This methodological separation of bug localization and fixing using different LLMs enables effective integration of diverse contextual information and improved incorporation of inductive biases. We introduce Toggle: Token-Granulated Bug Localization and Repair, a comprehensive program repair framework that integrates a bug localization model, an adjustment unit, and a bug-fixing model. Toggle takes a buggy function as input and generates a complete corrected function. We investigate various styles of prompting to the bug fixing model to identify the most effective prompts that better utilize the inductive bias and significantly outperform others. Toggle achieves the new state-of-the-art (SOTA) performance on the CodeXGLUE code refinement benchmark, and exhibits better and comparable performance on several other widely-used APR datasets, including Defects4J.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Apr 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 15; 2026: 10.

39 papers.

Sort:

By area:

  1. 2025Multi-SWE-bench: A Multilingual Benchmark for Issue Resolvingcited by 165
  2. 2024Large Language Models for Cyber Security: A Systematic Literature Reviewcited by 65
  3. 2024A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languagescited by 65
  4. 2024From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debuggingcited by 46
  5. 2024Can LLMs Replace Manual Annotation of Software Engineering Artifacts?cited by 40
  6. 2024LeDex: Training LLMs to Better Self-Debug and Explain Codecited by 39
  7. 2024Top Score on the Wrong Exam: On Benchmarking in Machine Learning for Vulnerability Detectioncited by 27
  8. 2025QualityFlow: An Agentic Workflow for Program Synthesis Controlled by LLM Quality Checkscited by 22
  9. 2024Collu-Bench: A Benchmark for Predicting Language Model Hallucinations in Codecited by 13
  10. 2024Enhancing Automated Program Repair with Solution Designcited by 8
  11. 2024LATTE: Improving Latex Recognition for Tables and Formulae with Iterative Refinementcited by 8
  12. 2024Location is Key: Leveraging Large Language Model for Functional Bug Localization in Verilogcited by 8
27 more
  1. 2025Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMscited by 6
  2. 2026TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Codecited by 6
  3. 2024Integrating Various Software Artifacts for Better LLM-based Bug Localization and Program Repaircited by 4
  4. 2025AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Modelcited by 4
  5. 2025NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debuggingcited by 4
  6. 2025Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilitiescited by 4
  7. 2024"You still have to study" -- On the Security of LLM generated codecited by 3
  8. 2025Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinementcited by 3
  9. 2026Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repaircited by 3
  10. 2024Code Vulnerability Repair with Large Language Model using Context-Aware Prompt Tuningcited by 2
  11. 2025Treefix: Enabling Execution with a Tree of Prefixescited by 2
  12. 2025WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at WhatsAppcited by 2
  13. 2025Multicalibration for LLM-based Code Generationcited by 2
  14. 2026ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localizationcited by 2
  15. 2025PRIMG : Efficient LLM-driven Test Generation Using Mutant Prioritizationcited by 1
  16. 2025Towards Functional Correctness of Large Code Models with Selective Generationcited by 1
  17. 2026Multi-task Code LLMs: Data Mix or Model Merge?cited by 1
  18. 2026Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiencycited by 1
  19. 2024Selection of Prompt Engineering Techniques for Code Generation through Predicting Code Complexitycited by 0
  20. 2025Towards Reliable LLM-Driven Fuzz Testing: Vision and Road Aheadcited by 0
  21. 2025Leveraging LLM to Strengthen ML-Based Cross-Site Scripting Detectioncited by 0
  22. 2025CodeFlowLM: Incremental Just-In-Time Defect Prediction with Pretrained Language Models and Exploratory Insights into Defect Localizationcited by 0
  23. 2026On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Studycited by 0
  24. 2026Repository-Level Solidity Code Generation with Large Language Models: From Prompting to Fine-Tuningcited by 0
  25. 2026JupOtter: Cell-Level Bug Detection in Jupyter Notebookscited by 0
  26. 2026Predicting Program Exit Code with LLMs and Programming Language Semanticscited by 0
  27. 2026On the Lexical Superstition of Large Language Models for Code Comprehension: Re-evaluation on Code of Low Lexical Qualitycited by 0