中文
相关论文

相关论文: Repair-R1: Better Test Before Repair

200 篇论文

Automated Program Repair (APR) techniques have shown more and more promising results in fixing real-world bugs. Despite the effectiveness, APR techniques still face an overfitting problem: a generated patch can be incorrect although it…

软件工程 · 计算机科学 2024-03-26 Xin Zhou , Bowen Xu , Kisub Kim , DongGyun Han , Thanh Le-Cong , Junda He , Bach Le , David Lo

In recent years, Automated Program Repair (APR) techniques specifically designed for quantum programs have been proposed. However, existing approaches often suffer from low repair success rates or poor understandability of the generated…

LLMs have garnered considerable attention for their potential to streamline Automated Program Repair (APR). LLM-based approaches can either insert the correct code or directly generate patches when provided with buggy methods. However, most…

软件工程 · 计算机科学 2025-09-30 Qiong Feng , Xiaotian Ma , Jiayi Sheng , Ziyuan Feng , Wei Song , Peng Liang

Machine learning models commonly exhibit unexpected failures post-deployment due to either data shifts or uncommon situations in the training environment. Domain experts typically go through the tedious process of inspecting the failure…

Large language models are increasingly used to produce runnable software. In practice, security is often addressed through a Detect--Repair--Verify (DRV) loop that detects issues, applies fixes, and verifies the result. This work studies…

软件工程 · 计算机科学 2026-03-03 Cheng Cheng

Large language models (LLMs) are reshaping automated program repair. We present a unified taxonomy that groups 62 recent LLM-based repair systems into four paradigms defined by parameter adaptation and control authority over the repair…

软件工程 · 计算机科学 2025-12-05 Boyang Yang , Zijian Cai , Fengling Liu , Bach Le , Lingming Zhang , Tegawendé F. Bissyandé , Yang Liu , Haoye Tian

Unit testing is crucial for detecting bugs in individual program units but consumes time and effort. Recently, large language models (LLMs) have demonstrated remarkable capabilities in generating unit test cases. However, several problems…

软件工程 · 计算机科学 2025-04-01 Siqi Gu , Quanjun Zhang , Kecheng Li , Chunrong Fang , Fangyuan Tian , Liuchuan Zhu , Jianyi Zhou , Zhenyu Chen

Automated program repair (APR) techniques are effective in fixing inevitable defects in software, enhancing development efficiency and software robustness. However, due to the difficulty of generating precise specifications, existing APR…

软件工程 · 计算机科学 2025-10-17 Xu He , Shu Wang , Kun Sun

Automated Program Repair (APR) is defined as the process of fixing a bug/defect in the source code, by an automated tool. APR tools have recently experienced promising results by leveraging state-of-the-art Neural Language Processing (NLP)…

软件工程 · 计算机科学 2023-01-13 Armin Zirak , Hadi Hemmati

We revisit the performance of template-based APR to build comprehensive knowledge about the effectiveness of fix patterns, and to highlight the importance of complementary steps such as fault localization or donor code retrieval. To that…

软件工程 · 计算机科学 2019-06-07 Kui Liu , Anil Koyuncu , Dongsun Kim , Tegawendé F. Bissyandé

Automated program repair (APR) using deep learning techniques has become an important area of research in recent years, aiming to automatically generate bug-fixing patches that can improve software reliability and maintainability. However,…

软件工程 · 计算机科学 2024-05-08 Reza Gharibi , Mohammad Hadi Sadreddini , Seyed Mostafa Fakhrahmad

Large Language Models (LLMs) have revolutionized automated program repair (APR) but current benchmarks like SWE-Bench predominantly focus on userspace applications and overlook the complexities of kernel-space debugging and repair. The…

软件工程 · 计算机科学 2025-11-21 Kareem Shehada , Yifan Wu , Wyatt D. Feng , Adithya Iyer , Gryphon Kumfert , Yangruibo Ding , Zhiyun Qian

Most programmers make mistakes when writing code. Some of these mistakes are small and require few edits to the original program -- a class of errors recently termed last mile mistakes. These errors break the flow for experienced developers…

软件工程 · 计算机科学 2022-12-06 Harshit Joshi , José Cambronero , Sumit Gulwani , Vu Le , Ivan Radicek , Gust Verbruggen

Program repair techniques offer cost-saving benefits for debugging within software development and programming education scenarios. With the proven effectiveness of Large Language Models (LLMs) in code-related tasks, researchers have…

软件工程 · 计算机科学 2024-07-09 Boyang Yang , Haoye Tian , Weiguo Pian , Haoran Yu , Haitao Wang , Jacques Klein , Tegawendé F. Bissyandé , Shunfu Jin

Recent advances in large language models (LLMs) have accelerated the development of AI-driven automated program repair (APR) solutions. However, these solutions are typically evaluated using static benchmarks such as Defects4J and…

软件工程 · 计算机科学 2025-10-01 Yinghang Ma , Jiho Shin , Leuson Da Silva , Zhen Ming , Jiang , Song Wang , Foutse Khomh , Shin Hwei Tan

In introductory programming courses, it is challenging for instructors to provide debugging feedback on students' incorrect programs. Some recent tools automatically offer program repair feedback by identifying any differences between…

软件工程 · 计算机科学 2021-07-15 Yunlong Lu , Na Meng , Wenxin Li

Large language models (LLMs) inevitably make mistakes when performing step-by-step mathematical reasoning. Process Reward Models (PRMs) have emerged as a promising solution by evaluating each reasoning step. However, existing PRMs typically…

计算与语言 · 计算机科学 2025-03-28 Shuaijie She , Junxiao Liu , Yifeng Liu , Jiajun Chen , Xin Huang , Shujian Huang

Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…

计算与语言 · 计算机科学 2026-02-11 Yisu Wang , Ming Wang , Haoyuan Song , Wenjie Huang , Chaozheng Wang , Yi Xie , Xuming Ran

This study explores the potential of Large Language Models (LLMs) in automating the repair of C programs. We present a framework that integrates spectrum-based fault localization (SBFL), runtime feedback, and Chain-of-Thought-structured…

软件工程 · 计算机科学 2025-09-04 Mahdi Farzandway , Fatemeh Ghassemi

Automated program repair (APR) attempts to generate correct patches and has drawn wide attention from both academia and industry in the past decades. However, APR is continuously struggling with the patch overfitting issue due to the weak…

软件工程 · 计算机科学 2026-04-07 Quanjun Zhang , Haichuan Hu , Chunrong Fang , Ye Shang , Tao Zheng , Zhenyu Chen , Yun Yang , Liang Xiao