# Empirical Review of Java Program Repair Tools: A Large-Scale Experiment on 2,141 Bugs and 23,551 Repair Attempts

arXiv: https://arxiv.org/abs/1905.11973 · HTML: https://mlsanity.com/paper/1905.11973/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2019.

## Built on by (most cited first, 12 of 12)

- [Large Language Models for Test-Free Fault Localization](https://mlsanity.com/paper/2310.01726/) (2023)
- [A Syntax-Guided Edit Decoder for Neural Program Repair](https://mlsanity.com/paper/2106.08253/) (2021)
- [DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletons](https://mlsanity.com/paper/2105.09352/) (2021)
- [RunBugRun -- An Executable Dataset for Automated Program Repair](https://mlsanity.com/paper/2304.01102/) (2023)
- [Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems](https://mlsanity.com/paper/2506.17208/) (2025)
- [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)
- [Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generation](https://mlsanity.com/paper/2410.16655/) (2024)
- [CCRep: Learning Code Change Representations via Pre-Trained Code Model and Query Back](https://mlsanity.com/paper/2302.03924/) (2023)
- [RePaCA: Leveraging Reasoning Large Language Models for Static Automated Patch Correctness Assessment](https://mlsanity.com/paper/2507.22580/) (2025)
- [BigIssue: A Realistic Bug Localization Benchmark](https://mlsanity.com/paper/2207.10739/) (2022)
- [A Metamorphic Testing Approach to Diagnosing Memorization in LLM-Based Program Repair](https://mlsanity.com/paper/2604.21579/) (2026)
- [Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities](https://mlsanity.com/paper/2609.15963/) (2026)

## Abstract (arXiv)

In the past decade, research on test-suite-based automatic program repair has grown significantly. Each year, new approaches and implementations are featured in major software engineering venues. However, most of those approaches are evaluated on a single benchmark of bugs, which are also rarely reproduced by other researchers. In this paper, we present a large-scale experiment using 11 Java test-suite-based repair tools and 5 benchmarks of bugs. Our goal is to have a better understanding of the current state of automatic program repair tools on a large diversity of benchmarks. Our investigation is guided by the hypothesis that the repairability of repair tools might not be generalized across different benchmarks of bugs. We found that the 11 tools 1) are able to generate patches for 21% of the bugs from the 5 benchmarks, and 2) have better performance on Defects4J compared to other benchmarks, by generating patches for 47% of the bugs from Defects4J compared to 10-30% of bugs from the other benchmarks. Our experiment comprises 23,551 repair attempts in total, which we used to find the causes of non-patch generation. These causes are reported in this paper, which can help repair tool designers to improve their techniques and tools.