# ITER: Iterative Neural Repair for Multi-Location Patches

arXiv: https://arxiv.org/abs/2304.12015 · HTML: https://mlsanity.com/paper/2304.12015/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 65 references that are in the map.
- First posted on arXiv 24 Apr 2023.

## Builds on (most cited first, 29 of 29)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair](https://mlsanity.com/paper/1901.01808/) (2018)
- [An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation](https://mlsanity.com/paper/1812.08693/) (2018)
- [Graph-based, Self-Supervised Program Repair from Diagnostic Feedback](https://mlsanity.com/paper/2005.10636/) (2020)
- [CURE: Code-Aware Neural Machine Translation for Automatic Program Repair](https://mlsanity.com/paper/2103.00073/) (2021)
- [Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning](https://mlsanity.com/paper/2207.08281/) (2022)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [Automated Repair of Programs from Large Language Models](https://mlsanity.com/paper/2205.10583/) (2022)
- [TBar: Revisiting Template-based Automated Program Repair](https://mlsanity.com/paper/1903.08409/) (2019)
- [Self-Supervised Bug Detection and Repair](https://mlsanity.com/paper/2105.12787/) (2021)
- [A Syntax-Guided Edit Decoder for Neural Program Repair](https://mlsanity.com/paper/2106.08253/) (2021)
- [On Learning Meaningful Code Changes via Neural Machine Translation](https://mlsanity.com/paper/1901.09102/) (2019)
- [Neural Program Repair with Execution-based Backpropagation](https://mlsanity.com/paper/2105.04123/) (2021)
- [CODIT: Code Editing with Tree-Based Neural Models](https://mlsanity.com/paper/1810.00314/) (2018)
- [SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics](https://mlsanity.com/paper/2203.12755/) (2022)
- [Nopol: Automatic Repair of Conditional Statement Bugs in Java Programs](https://mlsanity.com/paper/1811.04211/) (2018)
- [ARJA: Automated Repair of Java Programs via Multi-Objective Genetic Programming](https://mlsanity.com/paper/1712.07804/) (2017)
- [On Multi-Modal Learning of Editing Source Code](https://mlsanity.com/paper/2108.06645/) (2021)
- [Automatic Software Repair: a Bibliography](https://mlsanity.com/paper/1807.00515/) (2018)
- [Trust Enhancement Issues in Program Repair](https://mlsanity.com/paper/2108.13064/) (2021)
- [DEAR: A Novel Deep Learning-based Approach for Automated Program Repair](https://mlsanity.com/paper/2205.01859/) (2022)
- [Practical Program Repair via Bytecode Mutation](https://mlsanity.com/paper/1807.03512/) (2018)
- [A Comprehensive Study of Automatic Program Repair on the QuixBugs Benchmark](https://mlsanity.com/paper/1805.03454/) (2018)
- [On the Efficiency of Test Suite based Program Repair: A Systematic Assessment of 16 Automated Repair Systems for Java Programs](https://mlsanity.com/paper/2008.00914/) (2020)
- [Elixir: Effective object-oriented program repair](https://mlsanity.com/paper/2112.10915/) (2021)
- [Precise Condition Synthesis for Program Repair](https://mlsanity.com/paper/1608.07754/) (2016)
- [KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair](https://mlsanity.com/paper/2302.01857/) (2023)
- [Harnessing Evolution for Multi-Hunk Program Repair](https://mlsanity.com/paper/1906.08903/) (2019)
- [Dynamic Patch Generation for Null Pointer Exceptions using Metaprogramming](https://mlsanity.com/paper/1812.00409/) (2018)

## Built on by (most cited first, 16 of 16)

- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale](https://mlsanity.com/paper/2409.16299/) (2024)
- [RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair](https://mlsanity.com/paper/2312.15698/) (2023)
- [Can LLMs Replace Manual Annotation of Software Engineering Artifacts?](https://mlsanity.com/paper/2408.05534/) (2024)
- [Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories](https://mlsanity.com/paper/2511.00197/) (2025)
- [Search-Based LLMs for Code Optimization](https://mlsanity.com/paper/2408.12159/) (2024)
- [Agent READMEs: An Empirical Study of Context Files for Agentic Coding](https://mlsanity.com/paper/2511.12884/) (2025)
- [The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models](https://mlsanity.com/paper/2505.02931/) (2025)
- [REFINE: Enhancing Program Repair Agents through Context-Aware Patch Refinement](https://mlsanity.com/paper/2510.03588/) (2025)
- [Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation](https://mlsanity.com/paper/2410.16655/) (2024)
- [Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Prompting](https://mlsanity.com/paper/2411.15442/) (2024)
- [DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information](https://mlsanity.com/paper/2512.24635/) (2025)
- [Treefix: Enabling Execution with a Tree of Prefixes](https://mlsanity.com/paper/2501.12339/) (2025)
- [Beyond Accuracy: Behavioral Dynamics of Agentic Multi-Hunk Repair](https://mlsanity.com/paper/2511.11012/) (2025)
- [MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs](https://mlsanity.com/paper/2607.26591/) (2026)

## 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.