中文
相关论文

相关论文: BackportBench: A Multilingual Benchmark for Automa…

200 篇论文

Patch backporting, the process of migrating mainline security patches to older branches, is an essential task in maintaining popular open-source projects (e.g., Linux kernel). However, manual backporting can be labor-intensive, while…

密码学与安全 · 计算机科学 2025-10-28 Zhaoyang Li , Zheng Yu , Jingyi Song , Meng Xu , Yuxuan Luo , Dongliang Mu

Source code repositories allow developers to manage multiple versions (or branches) of a software system. Pull-requests are used to modify a branch, and backporting is a regular activity used to port changes from a current development…

软件工程 · 计算机科学 2022-04-11 Debasish Chakroborti , Kevin A. Schneider , Chanchal K. Roy

Maintaining software is an ongoing process that stretches beyond the initial release. Stable software versions continuously evolve to fix bugs, add improvements, address security issues, and ensure compatibility. This ongoing support…

软件工程 · 计算机科学 2025-11-13 Jarin Tasnim , Debasish Chakroborti , Chanchal K. Roy , Kevin A. Schneider

Timely and effective vulnerability patching is essential for cybersecurity defense, for which various approaches have been proposed yet still struggle to generate valid and correct patches for real-world vulnerabilities. In this paper, we…

密码学与安全 · 计算机科学 2025-04-04 Yu Nong , Haoran Yang , Long Cheng , Hongxin Hu , Haipeng Cai

Quantitative backtesting is essential for evaluating trading strategies but remains hampered by high technical barriers and limited scalability. While Large Language Models (LLMs) offer a transformative path to automate this complex,…

计算与语言 · 计算机科学 2026-05-26 Zhensheng Wang , Wenmian Yang , Qingtai Wu , Lequan Ma , Yiquan Zhang , Weijia Jia

The evolution of AI coding agents has shifted the frontier from simple snippet completion to autonomous repository-level engineering. However, evaluating these agents remains ill-posed in general code repository generation, where the lack…

软件工程 · 计算机科学 2026-02-27 Xuefeng Li , Nir Ben-Israel , Yotam Raz , Belal Ahmed , Doron Serebro , Antoine Raux

Automated Vulnerability Repair (AVR) systems, especially those leveraging large language models (LLMs), have demonstrated promising results in patching vulnerabilities -- that is, if we trust their patch validation methodology. Ground-truth…

软件工程 · 计算机科学 2026-03-23 Zheng Yu , Wenxuan Shi , Xinqian Sun , Zheyun Feng , Meng Xu , Xinyu Xing

Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the…

Logging statements are central to debugging, failure diagnosis, and production observability, yet writing them requires developers to decide where to place a logging statement, which API and severity level to use, and what runtime…

软件工程 · 计算机科学 2026-04-21 Renyi Zhong , Yichen Li , Yulun Wu , Jinxi Kuang , Yintong Huo , Michael R. Lyu

Automatic program generation has long been a fundamental challenge in computer science. Recent benchmarks have shown that large language models (LLMs) can effectively generate code at the function level, make code edits, and solve…

Open-source software vulnerability patch detection is a critical component for maintaining software security and ensuring software supply chain integrity. Traditional manual detection methods face significant scalability challenges when…

软件工程 · 计算机科学 2025-09-30 Haoran Xu , Chen Zhi , Junxiao Han , Xinkui Zhao , Jianwei Yin , Shuiguang Deng

Debugging software remains a labor-intensive and time-consuming process despite advances in testing and verification. Learning-based automated program repair (APR) has shown promise in reducing the effort of manually fixing bugs. However,…

软件工程 · 计算机科学 2026-04-14 Reza Gharibi , Mohammad Hadi Sadreddini , Seyed Mostafa Fakhrahmad

Continuous Integration (CI) enforces repository-level correctness through multi-stage workflows and is central to modern software development, yet diagnosing and repairing CI failures remains challenging. Unlike traditional program repair,…

软件工程 · 计算机科学 2026-05-06 Rabeya Khatun Muna , Md Nakhla Rafi , Tse-Hsun , Chen

Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existing benchmarks focus predominantly on single-issue bug fixes…

Large Language Models (LLMs) have emerged as promising tools in software development, enabling automated code generation and analysis. However, their knowledge is limited to a fixed cutoff date, making them prone to generating code…

密码学与安全 · 计算机科学 2025-12-01 Minjae Seo , Wonwoo Choi , Myoungsung You , Seungwon Shin

Modern Large Language Model (LLM) agents promise end to end assistance with real-world software tasks, yet existing benchmarks evaluate LLM agents almost exclusively in pre-baked environments where every dependency is pre-installed. To fill…

软件工程 · 计算机科学 2025-07-15 Avi Arora , Jinu Jang , Roshanak Zilouchian Moghaddam

Software vulnerabilities pose critical security risks, demanding prompt and effective mitigation strategies. While advancements in Automated Program Repair (APR) have primarily targeted general software bugs, the domain of vulnerability…

软件工程 · 计算机科学 2025-01-14 Zanis Ali Khan , Aayush Garg , Yuejun Guo , Qiang Tang

Bug fixing holds significant importance in software development and maintenance. Recent research has made substantial strides in exploring the potential of large language models (LLMs) for automatically resolving software bugs. However, a…

软件工程 · 计算机科学 2025-02-18 Yuwei Zhang , Zhi Jin , Ying Xing , Ge Li , Fang Liu , Jiaxin Zhu , Wensheng Dou , Jun Wei

The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks…

Large Language Models have advanced automated software development, however, it remains a challenge to correctly infer dependencies, namely, identifying the internal components and external packages required for a repository to successfully…

‹ 上一页 1 2 3 10 下一页 ›