# Neural Program Repair with Execution-based Backpropagation

arXiv: https://arxiv.org/abs/2105.04123 · HTML: https://mlsanity.com/paper/2105.04123/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 May 2021.

## Built on by (most cited first, 30 of 50)

- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://mlsanity.com/paper/2406.01304/) (2024)
- [Is ChatGPT the Ultimate Programming Assistant -- How far is it?](https://mlsanity.com/paper/2304.11938/) (2023)
- [Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repair](https://mlsanity.com/paper/2309.00608/) (2023)
- [How Effective Are Neural Networks for Fixing Security Vulnerabilities](https://mlsanity.com/paper/2305.18607/) (2023)
- [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://mlsanity.com/paper/2309.06057/) (2023)
- [Conversational Automated Program Repair](https://mlsanity.com/paper/2301.13246/) (2023)
- [Automatic Programming: Large Language Models and Beyond](https://mlsanity.com/paper/2405.02213/) (2024)
- [Understanding Code Agent Behaviour: An Empirical Study of Success and Failure Trajectories](https://mlsanity.com/paper/2511.00197/) (2025)
- [Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review](https://mlsanity.com/paper/2307.02503/) (2023)
- [Better patching using LLM prompting, via Self-Consistency](https://mlsanity.com/paper/2306.00108/) (2023)
- [Rectifier: Code Translation with Corrector via LLMs](https://mlsanity.com/paper/2407.07472/) (2024)
- [ITER: Iterative Neural Repair for Multi-Location Patches](https://mlsanity.com/paper/2304.12015/) (2023)
- [KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair](https://mlsanity.com/paper/2302.01857/) (2023)
- [Aligning the Objective of LLM-based Program Repair](https://mlsanity.com/paper/2404.08877/) (2024)
- [Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning](https://mlsanity.com/paper/2301.01113/) (2023)
- [RunBugRun -- An Executable Dataset for Automated Program Repair](https://mlsanity.com/paper/2304.01102/) (2023)
- [Improving Automated Program Repair with Domain Adaptation](https://mlsanity.com/paper/2212.11414/) (2022)
- [Exploiting Code Symmetries for Learning Program Semantics](https://mlsanity.com/paper/2308.03312/) (2023)
- [Extending the Frontier of ChatGPT: Code Generation and Debugging](https://mlsanity.com/paper/2307.08260/) (2023)
- [Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness](https://mlsanity.com/paper/2208.04125/) (2022)
- [LExecutor: Learning-Guided Execution](https://mlsanity.com/paper/2302.02343/) (2023)
- [Revisiting the Plastic Surgery Hypothesis via Large Language Models](https://mlsanity.com/paper/2303.10494/) (2023)
- [Automated Program Repair: Emerging trends pose and expose problems for benchmarks](https://mlsanity.com/paper/2405.05455/) (2024)
- [Exploring the Limits of ChatGPT in Software Security Applications](https://mlsanity.com/paper/2312.05275/) (2023)
- [Repair-R1: Better Test Before Repair](https://mlsanity.com/paper/2507.22853/) (2025)
- [The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification](https://mlsanity.com/paper/2305.04940/) (2023)
- [Frustrated with Code Quality Issues? LLMs can Help!](https://mlsanity.com/paper/2309.12938/) (2023)
- [Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing](https://mlsanity.com/paper/2402.11892/) (2024)

## Abstract (arXiv)

Neural machine translation (NMT) architectures have achieved promising results for automatic program repair. Yet, they have the limitation of generating low-quality patches (e.g., not compilable patches). This is because the existing works only optimize a purely syntactic loss function based on characters and tokens without incorporating program-specific information during neural network weight optimization. In this paper, we propose a novel program repair model called RewardRepair. The core novelty of RewardRepair is to improve NMT-based program repair with a loss function based on program compilation and test execution information, rewarding the network to produce patches that compile and that do not overfit. We conduct several experiments to evaluate RewardRepair showing that it is feasible and effective to use compilation and test execution results to optimize the underlying neural repair model. RewardRepair correctly repairs 207 bugs over four benchmarks. we report on repair success for 121 bugs that are fixed for the first time in the literature. Also, RewardRepair produces up to 45.3% of compilable patches, an improvement over the 39% by the state-of-the-art.