Automated program repair

By Claire Le Goues, Michael Pradel, Abhik Roychoudhury. Communications of the ACM, 2019

489 citations recorded by the source corpus.

Automated program repair can relieve programmers from the burden of manually fixing the ever-increasing number of programming mistakes.

View Paper: https://www.semanticscholar.org/paper/b5abecf78c1bd975449e34350289a904e6ef35cc

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Mark Harman
2. Emily First
3. Qihao Zhu
4. Markus Norman Rabe
5. Shin Yoo
6. Yuriy Brun
7. Dweep Trivedi
8. Angela Fan

Citations in the corpus

• Baldur: Whole-Proof Generation and Repair with Large Language Models (2023, methodology): “The automated program repair field studies the task of taking a program with a bug, evidenced by one or more failing tests, and automatically producing a modified version of the program that passes all the tests [50].”
• Scaffle: bug localization on millions of files (2020, methodology): “Moreover, identifying the file to fix can serve as a first step in automated program repair [14].”
• Getafix: learning to fix bugs automatically (2019, methodology): “The Getafix approach and the constraints that motivated it differ from the assumptions made by automated program repair techniques [Goues et al. 2019], the most practical of which for large systems are generate-and-validate repair systems [Goues et al.”
• Learning to Synthesize Programs as Interpretable and Generalizable Policies (2021, background): “[109] Claire Le Goues, Michael Pradel, and Abhik Roychoudhury.”
• A syntax-guided edit decoder for neural program repair (2021, background): “For a thorough discussion of APR, existing surveys [13, 17, 50, 51] are recommended to readers.”
• Large Language Models for Software Engineering: Survey and Open Problems (2023, methodology): “To address this issue, we can refer to the well-established literature on software repair [45], [142], grounded in over two decades of the development of search-based approaches to software engineering [11], [143].”
• AutoCodeRover: Autonomous Program Improvement (2024, unknown): “Recent progress in large language models (LLMs) and the appearance of tools like Github Copilot [26] hold significant promise in automatic programming.”
• Repairing Bugs in Python Assignments Using Large Language Models (2022, background): “The field of automated program repair (APR), which has a long history in the software engineering community [2]–[7], has introduced different approaches [8]–[11] to produce such automated repairs for student mistakes in introductory assignments.”