A Survey of Learning-based Automated Program Repair

Abstract

Automated program repair (APR) aims to fix software bugs automatically and plays a crucial role in software development and maintenance. With the recent advances in deep learning (DL), an increasing number of APR techniques have been proposed to leverage neural networks to learn bug-fixing patterns from massive opensource code repositories. Such learning-based techniques usually treat APR as a neural machine translation (NMT) task, where buggy code snippets (i.e., source language) are translated into fixed code snippets (i.e., target language) automatically. Benefiting from the powerful capability of DL to learn hidden relationships from previous bug-fixing datasets, learning-based APR techniques have achieved remarkable performance.In this paper, we provide a systematic survey to summarize the current state-of-the-art research in the learning-based APR community. We illustrate the general workflow of learning-based APR techniques and detail the crucial components, including fault localization, patch generation, patch ranking, patch validation, and patch correctness phases. We then discuss the widely-adopted datasets and evaluation metrics and outline existing empirical studies. We discuss several critical aspects of learning-based APR techniques, such as repair domains, industrial deployment, and the open science issue. We highlight several practical guidelines on applying DL techniques for future APR studies, such as exploring explainable patch generation and utilizing code features. Overall, our paper can help researchers gain a comprehensive understanding about the achievements of the existing learning-based APR techniques and promote the practical application of these techniques. Our artifacts are publicly available at https://github.com/QuanjunZhang/AwesomeLearningAPR. CCS Concepts: • Software and its engineering → Software testing and debugging; Software testing and debugging.

ChatGPT for Education and Research: Opportunities, Threats, and Strategies

“…Programming skills are acquired through repeated practice. To assist programmers, deep-learning-based tools are introduced for code repair, completion, error detection, optimization, verification, and classification [1,2,19,20,53,54]. In recent years, LLMs based on the Transformer architecture (e.g., CodeBERT, Codex, and PyMT5) have achieved state-of-the-art results for various programming tasks [55].…”

ChatGPT for Education and Research: Opportunities, Threats, and Strategies

“…Programming skills are acquired through repeated practice. To assist programmers, deep learning based tools are introduced for code repair, completion, error detection, optimization, verification, and classification [1,2,19,20,45,46]. In recent years, LLMs based on the Transformer architecture (e.g., CodeBERT, Codex, and PyMT5) have achieved state-of-the-art results for various programming tasks [47].…”

Towards Low-Resource Automatic Program Repair with Meta-Learning and Pretrained Language Models

“…Automatic Program Repair (APR) Recently, there is a growing body of APR research that aims to automate the rectification of software defects with less human intervention. In general, conventional APR approaches can be divided into three categories (Zhang et al, 2023(Zhang et al, , 2022, which are 1) heuristic-based (Goues et al, 2012;Qi et al, 2014;Jiang et al, 2018), 2) constraint-based (Martinez and Monperrus, 2018;Nguyen et al, 2013;Xuan et al, 2017), 3) template-based approaches Koyuncu et al, 2020).…”