mlsanityData to 7 Oct 2026

ITER: Iterative Neural Repair for Multi-Location Patches

arXiv 2304.12015 ↗First posted 24 Apr 2023cs.SE cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

Automated program repair (APR) has achieved promising results, especially using neural networks. Yet, the overwhelming majority of patches produced by APR tools are confined to one single location. When looking at the patches produced with neural repair, most of them fail to compile, while a few uncompilable ones go in the right direction. In both cases, the fundamental problem is to ignore the potential of partial patches. In this paper, we propose an iterative program repair paradigm called ITER founded on the concept of improving partial patches until they become plausible and correct. First, ITER iteratively improves partial single-location patches by fixing compilation errors and further refining the previously generated code. Second, ITER iteratively improves partial patches to construct multi-location patches, with fault localization re-execution. ITER is implemented for Java based on battle-proven deep neural networks and code representation. ITER is evaluated on 476 bugs from 10 open-source projects in Defects4J 2.0. ITER succeeds in repairing 15.5% of them, including 9 uniquely repaired multi-location bugs.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 29 of its 65 references that are in the map. First posted on arXiv 24 Apr 2023.

Builds on

29 of 65 references.

References · 29

  1. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  2. 2018SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repaircited by 144
  3. 2018An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translationcited by 106
  4. 2020Graph-based, Self-Supervised Program Repair from Diagnostic Feedbackcited by 93
  5. 2021CURE: Code-Aware Neural Machine Translation for Automatic Program Repaircited by 85
  6. 2022Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learningcited by 76
  7. 2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
  8. 2022Automated Repair of Programs from Large Language Modelscited by 71
  9. 2019TBar: Revisiting Template-based Automated Program Repaircited by 64
  10. 2021Self-Supervised Bug Detection and Repaircited by 59
  11. 2021A Syntax-Guided Edit Decoder for Neural Program Repaircited by 57
  12. 2019On Learning Meaningful Code Changes via Neural Machine Translationcited by 50
17 more
  1. 2021Neural Program Repair with Execution-based Backpropagationcited by 50
  2. 2018CODIT: Code Editing with Tree-Based Neural Modelscited by 40
  3. 2022SelfAPR: Self-supervised Program Repair with Test Execution Diagnosticscited by 33
  4. 2018Nopol: Automatic Repair of Conditional Statement Bugs in Java Programscited by 32
  5. 2017ARJA: Automated Repair of Java Programs via Multi-Objective Genetic Programmingcited by 26
  6. 2021On Multi-Modal Learning of Editing Source Codecited by 25
  7. 2018Automatic Software Repair: a Bibliographycited by 24
  8. 2021Trust Enhancement Issues in Program Repaircited by 22
  9. 2022DEAR: A Novel Deep Learning-based Approach for Automated Program Repaircited by 22
  10. 2018Practical Program Repair via Bytecode Mutationcited by 19
  11. 2018A Comprehensive Study of Automatic Program Repair on the QuixBugs Benchmarkcited by 17
  12. 2020On the Efficiency of Test Suite based Program Repair: A Systematic Assessment of 16 Automated Repair Systems for Java Programscited by 16
  13. 2021Elixir: Effective object-oriented program repaircited by 16
  14. 2016Precise Condition Synthesis for Program Repaircited by 13
  15. 2023KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repaircited by 13
  16. 2019Harnessing Evolution for Multi-Hunk Program Repaircited by 12
  17. 2018Dynamic Patch Generation for Null Pointer Exceptions using Metaprogrammingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 7; 2026: 1.

16 papers.

Sort:

By area:

  1. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repaircited by 225
  2. 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolutioncited by 132
  3. 2024HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scalecited by 61
  4. 2023RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repaircited by 50
  5. 2024Can LLMs Replace Manual Annotation of Software Engineering Artifacts?cited by 40
  6. 2025Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectoriescited by 30
  7. 2024Search-Based LLMs for Code Optimizationcited by 27
  8. 2025Agent READMEs: An Empirical Study of Context Files for Agentic Codingcited by 21
  9. 2025The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Modelscited by 7
  10. 2025REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinementcited by 6
  11. 2024Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generationcited by 5
  12. 2024Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Promptingcited by 3
4 more
  1. 2025DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Informationcited by 3
  2. 2025Treefix: Enabling Execution with a Tree of Prefixescited by 2
  3. 2025Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repaircited by 2
  4. 2026MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugscited by 0