# ARJA: Automated Repair of Java Programs via Multi-Objective Genetic Programming

arXiv: https://arxiv.org/abs/1712.07804 · HTML: https://mlsanity.com/paper/1712.07804/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2017.

## Built on by (most cited first, 26 of 26)

- [CURE: Code-Aware Neural Machine Translation for Automatic Program Repair](https://mlsanity.com/paper/2103.00073/) (2021)
- [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://mlsanity.com/paper/2309.06057/) (2023)
- [Automatic Programming: Large Language Models and Beyond](https://mlsanity.com/paper/2405.02213/) (2024)
- [Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Review](https://mlsanity.com/paper/2307.02503/) (2023)
- [Multi-Objectivizing Software Configuration Tuning (for a single performance concern)](https://mlsanity.com/paper/2106.01331/) (2021)
- [HDLdebugger: Streamlining HDL debugging with Large Language Models](https://mlsanity.com/paper/2403.11671/) (2024)
- [MMO: Meta Multi-Objectivization for Software Configuration Tuning](https://mlsanity.com/paper/2112.07303/) (2021)
- [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)
- [RunBugRun -- An Executable Dataset for Automated Program Repair](https://mlsanity.com/paper/2304.01102/) (2023)
- [Enhanced Automated Code Vulnerability Repair using Large Language Models](https://mlsanity.com/paper/2401.03741/) (2024)
- [Automated Program Repair: Emerging trends pose and expose problems for benchmarks](https://mlsanity.com/paper/2405.05455/) (2024)
- [TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignment](https://mlsanity.com/paper/2409.19894/) (2024)
- [The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models](https://mlsanity.com/paper/2505.02931/) (2025)
- [Repair-R1: Better Test Before Repair](https://mlsanity.com/paper/2507.22853/) (2025)
- [Out of Context: How important is Local Context in Neural Program Repair?](https://mlsanity.com/paper/2312.04986/) (2023)
- [Predicting Patch Correctness Based on the Similarity of Failing Test Cases](https://mlsanity.com/paper/2107.13296/) (2021)
- [AuPair: Golden Example Pairs for Code Repair](https://mlsanity.com/paper/2502.18487/) (2025)
- [New Core-Guided and Hitting Set Algorithms for Multi-Objective Combinatorial Optimization](https://mlsanity.com/paper/2204.10856/) (2022)
- [ParLS-PBO: A Parallel Local Search Solver for Pseudo Boolean Optimization](https://mlsanity.com/paper/2407.21729/) (2024)
- [From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs](https://mlsanity.com/paper/2506.13182/) (2025)
- [Iterative Genetic Improvement: Scaling Stochastic Program Synthesis](https://mlsanity.com/paper/2202.13040/) (2022)
- [NARRepair: Non-Autoregressive Code Generation Model for Automatic Program Repair](https://mlsanity.com/paper/2406.16526/) (2024)
- [Self-Bootstrapping Automated Program Repair: Using LLMs to Generate and Evaluate Synthetic Training Data for Bug Repair](https://mlsanity.com/paper/2505.07372/) (2025)
- [AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code Adaptation](https://mlsanity.com/paper/2608.04459/) (2026)

## Abstract (arXiv)

Recent empirical studies show that the performance of GenProg is not satisfactory, particularly for Java. In this paper, we propose ARJA, a new GP based repair approach for automated repair of Java programs. To be specific, we present a novel lower-granularity patch representation that properly decouples the search subspaces of likely-buggy locations, operation types and potential fix ingredients, enabling GP to explore the search space more effectively. Based on this new representation, we formulate automated program repair as a multi-objective search problem and use NSGA-II to look for simpler repairs. To reduce the computational effort and search space, we introduce a test filtering procedure that can speed up the fitness evaluation of GP and three types of rules that can be applied to avoid unnecessary manipulations of the code. Moreover, we also propose a type matching strategy that can create new potential fix ingredients by exploiting the syntactic patterns of the existing statements. We conduct a large-scale empirical evaluation of ARJA along with its variants on both seeded bugs and real-world bugs in comparison with several state-of-the-art repair approaches. Our results verify the effectiveness and efficiency of the search mechanisms employed in ARJA and also show its superiority over the other approaches. In particular, compared to jGenProg (an implementation of GenProg for Java), an ARJA version fully following the redundancy assumption can generate a test-suite adequate patch for more than twice the number of bugs (from 27 to 59), and a correct patch for nearly four times of the number (from 5 to 18), on 224 real-world bugs considered in Defects4J. Furthermore, ARJA is able to correctly fix several real multi-location bugs that are hard to be repaired by most of the existing repair approaches.