# Neural Program Repair by Jointly Learning to Localize and Repair

arXiv: https://arxiv.org/abs/1904.01720 · HTML: https://mlsanity.com/paper/1904.01720/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2019.

## Built on by (most cited first, 30 of 40)

- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Hypothesis Search: Inductive Reasoning with Language Models](https://mlsanity.com/paper/2309.05660/) (2023)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [Self-Supervised Bug Detection and Repair](https://mlsanity.com/paper/2105.12787/) (2021)
- [Large Language Models of Code Fail at Completing Code with Potential Bugs](https://mlsanity.com/paper/2306.03438/) (2023)
- [A Survey on Machine Learning Techniques for Source Code Analysis](https://mlsanity.com/paper/2110.09610/) (2021)
- [Understanding Neural Code Intelligence Through Program Simplification](https://mlsanity.com/paper/2106.03353/) (2021)
- [Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit](https://mlsanity.com/paper/2401.00288/) (2023)
- [Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code](https://mlsanity.com/paper/2205.11739/) (2022)
- [Memorization and Generalization in Neural Code Intelligence Models](https://mlsanity.com/paper/2106.08704/) (2021)
- [On Distribution Shift in Learning-based Bug Detectors](https://mlsanity.com/paper/2204.10049/) (2022)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [Neurosymbolic Repair for Low-Code Formula Languages](https://mlsanity.com/paper/2207.11765/) (2022)
- [Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions](https://mlsanity.com/paper/2203.03771/) (2022)
- [Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5](https://mlsanity.com/paper/2211.14875/) (2022)
- [Improving Automated Program Repair with Domain Adaptation](https://mlsanity.com/paper/2212.11414/) (2022)
- [What does Transformer learn about source code?](https://mlsanity.com/paper/2207.08466/) (2022)
- [Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar](https://mlsanity.com/paper/2204.06643/) (2022)
- [LExecutor: Learning-Guided Execution](https://mlsanity.com/paper/2302.02343/) (2023)
- [DeepCode AI Fix: Fixing Security Vulnerabilities with Large Language Models](https://mlsanity.com/paper/2402.13291/) (2024)
- [Learning Program Representations with a Tree-Structured Transformer](https://mlsanity.com/paper/2208.08643/) (2022)
- [Learning Defect Prediction from Unrealistic Data](https://mlsanity.com/paper/2311.00931/) (2023)
- [A Survey of Deep Learning Models for Structural Code Understanding](https://mlsanity.com/paper/2205.01293/) (2022)
- [Can we learn from developer mistakes? Learning to localize and repair real bugs from real bug fixes](https://mlsanity.com/paper/2207.00301/) (2022)
- [Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces](https://mlsanity.com/paper/2505.17703/) (2025)
- [AdaptivePaste: Code Adaptation through Learning Semantics-aware Variable Usage Representations](https://mlsanity.com/paper/2205.11023/) (2022)
- [Jointly Learning to Repair Code and Generate Commit Message](https://mlsanity.com/paper/2109.12296/) (2021)
- [JEMMA: An Extensible Java Dataset for ML4Code Applications](https://mlsanity.com/paper/2212.09132/) (2022)
- [Study of Distractors in Neural Models of Code](https://mlsanity.com/paper/2303.01739/) (2023)

## Abstract (arXiv)

Due to its potential to improve programmer productivity and software quality, automated program repair has been an active topic of research. Newer techniques harness neural networks to learn directly from examples of buggy programs and their fixes. In this work, we consider a recently identified class of bugs called variable-misuse bugs. The state-of-the-art solution for variable misuse enumerates potential fixes for all possible bug locations in a program, before selecting the best prediction. We show that it is beneficial to train a model that jointly and directly localizes and repairs variable-misuse bugs. We present multi-headed pointer networks for this purpose, with one head each for localization and repair. The experimental results show that the joint model significantly outperforms an enumerative solution that uses a pointer based model for repair alone.