中文
相关论文

相关论文: Does Code Cleanliness Affect Coding Agents? A Cont…

200 篇论文

Developers spend 70% of their time understanding code. Code that is easy to read can save time, while hard-to-read code can lead to the introduction of bugs. However, it is difficult to establish what makes code more understandable.…

软件工程 · 计算机科学 2021-10-05 Delano Oliveira

Pull request (PR) descriptions generated by AI coding agents are the primary channel for communicating code changes to human reviewers. However, the alignment between these messages and the actual changes remains unexplored, raising…

软件工程 · 计算机科学 2026-01-27 Jingzhi Gong , Giovanni Pinna , Yixin Bian , Jie M. Zhang

Motivation: Code understandability is crucial in software development, as developers spend 58% to 70% of their time reading source code. Improving it can improve productivity and reduce maintenance costs. Problem: Experimental studies often…

Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have shifted toward realistic software evolution, but they rarely…

软件工程 · 计算机科学 2026-05-15 Man Ho Lam , Chaozheng Wang , Hange Liu , Jingyu Xiao , Haau-sing Li , Jen-tse Huang , Terry Yue Zhuo , Michael R. Lyu

Teams of interacting and co-operating agents have been proposed as an efficient and robust alternative to monolithic centralized control for carrying out specified tasks in a variety of applications. A number of different team and agent…

多智能体系统 · 计算机科学 2022-05-05 T. Wareham

AI coding assistants increasingly generate code alongside tests. How developers structure test code, whether inline with the implementation or in separate blocks, has traditionally been a matter of testing philosophy. We investigate whether…

软件工程 · 计算机科学 2026-04-23 Éric Jacopin

Recent advances in frontier large language models have enabled code review agents that operate in open-ended, reasoning-intensive settings. However, the lack of standardized benchmarks and granular evaluation protocols makes it difficult to…

软件工程 · 计算机科学 2026-03-13 Kristen Pereira , Neelabh Sinha , Rajat Ghosh , Debojyoti Dutta

Code review is a widespread practice to improve software quality and transfer knowledge. It is often seen as time-consuming due to the need for manual effort and potential delays. Several AI-assisted tools, such as Qodo, GitHub Copilot, and…

LLMs are increasingly embedded in programming workflows, from code generation to automated code review. Yet, how gendered communication styles interact with LLM-assisted programming and code review remains underexplored. We present a…

We present Code Broker, a multi agent system built on Google s Agent Development Kit ADK that analyses Python source code from individual files, local directory trees, or remote GitHub repositories and generates structured, actionable…

软件工程 · 计算机科学 2026-05-07 Samer Attrah

As AI agents increasingly contribute to code development and maintenance, there is still limited empirical evidence on the quality and risk characteristics of their changes in real-world projects, particularly for refactoring-oriented…

软件工程 · 计算机科学 2026-05-21 Mohamed Almukhtar , Anwar Ghammam , Hua Ming

AI assistance produces significant productivity gains across professional domains, particularly for novice workers. Yet how this assistance affects the development of skills required to effectively supervise AI remains unclear. Novice…

计算机与社会 · 计算机科学 2026-02-03 Judy Hanwen Shen , Alex Tamkin

Modern computing students often rely on both natural-language prompting and manual code editing to solve programming tasks. Yet we still lack a clear understanding of how these two modes are combined in practice, and how their usage varies…

Recently, workforce shortage has become a popular issue in information technology (IT). One solution to increasing the workforce supply is to increase the number of female IT professionals. This is because there is gender imbalance in…

软件工程 · 计算机科学 2022-09-09 Yuriko Takatsuka , Yukasa Murakami , Masateru Tsunoda , Masahide Nakamura

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with…

In recent years, large pre-trained Language Models of Code (CodeLMs) have shown promising results on various software engineering tasks. One such task is automatic code update recommendation, which transforms outdated code snippets into…

软件工程 · 计算机科学 2024-05-14 Yue Liu , Chakkrit Tantithamthavorn , Yonghui Liu , Patanamon Thongtanunam , Li Li

Recent research provides evidence that effective communication in collaborative software development has significant impact on the software development lifecycle. Although related qualitative and quantitative studies point out textual…

软件工程 · 计算机科学 2018-03-07 Vasiliki Efstathiou , Diomidis Spinellis

The costly human effort required to prepare the training data of machine learning (ML) models hinders their practical development and usage in software engineering (ML4Code), especially for those with limited budgets. Therefore, efficiently…

软件工程 · 计算机科学 2023-06-05 Qiang Hu , Yuejun Guo , Xiaofei Xie , Maxime Cordy , Lei Ma , Mike Papadakis , Yves Le Traon

Automatic testing is a widely adopted technique for improving software quality. Software developers add, remove and update test methods and test classes as part of the software development process as well as during the evolution phase,…

软件工程 · 计算机科学 2017-09-27 Stanislav Levin , Amiram Yehudai

Saving, or checkpointing, intermediate results during interactive data exploration can potentially boost user productivity. However, existing studies on this topic are limited, as they primarily rely on small-scale experiments with human…

人机交互 · 计算机科学 2025-04-03 Hanxi Fang , Supawit Chockchowwat , Hari Sundaram , Yongjoo Park
‹ 上一页 1 8 9 10 下一页 ›