Neural Program Repair: Systems, Challenges and Solutions

TL;DR

This paper reviews Neural Program Repair (NPR), a deep learning approach that automatically fixes bugs in source code by translating buggy code into correct code, highlighting architectures, challenges, and future directions.

Contribution

It provides a comprehensive overview of NPR systems, decomposes their architecture into modules, discusses challenges and solutions, and suggests future research directions.

Findings

NPR models treat program repair as a translation task.

NPR does not require test suites, enhancing applicability.

The paper identifies key challenges and discusses existing solutions.

Abstract

Automated Program Repair (APR) aims to automatically fix bugs in the source code. Recently, as advances in Deep Learning (DL) field, there is a rise of Neural Program Repair (NPR) studies, which formulate APR as a translation task from buggy code to correct code and adopt neural networks based on encoder-decoder architecture. Compared with other APR techniques, NPR approaches have a great advantage in applicability because they do not need any specification (i.e., a test suite). Although NPR has been a hot research direction, there isn't any overview on this field yet. In order to help interested readers understand architectures, challenges and corresponding solutions of existing NPR systems, we conduct a literature review on latest studies in this paper. We begin with introducing the background knowledge on this field. Next, to be understandable, we decompose the NPR procedure into a series of modules and explicate various design choices on each module. Furthermore, we identify several challenges and discuss the effect of existing solutions. Finally, we conclude and provide some promising directions for future research.