arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.20106cs.SE
收藏

我们是否都在以相同的方式使用代理?核心和边缘开发者对编码代理使用的一次实证研究

Are We All Using Agents the Same Way? An Empirical Study of Core and Peripheral Developers Use of Coding Agents

University of Saskatchewan(萨斯喀彻温大学)

Shamse Tasnim Cynthia, Joy Krishan Das, Banani Roy

AI总结:

本文通过实证研究发现,核心和边缘开发者在使用编码代理时存在差异,核心开发者更关注文档和测试,而边缘开发者更频繁使用代理进行任务分配。

摘要:

自主AI代理正在改变软件开发,并重新定义开发者与AI协作的方式。先前的研究表明,AI驱动工具的采用和使用在核心和边缘开发者之间存在差异。然而,这种动态在自主编码代理新兴时代如何展开仍不清楚。在本文中,我们对9427个代理PR进行了首次实证研究,研究核心和边缘开发者在接受之前如何使用、审查、修改和验证代理生成的贡献。通过定性和定量分析的混合方法,我们做出了四个关键贡献。首先,一部分边缘开发者更频繁地使用代理,将任务平均分配在修复bug、添加功能、文档和测试上。相比之下,核心开发者更关注文档和测试,但他们的代理PR经常被合并到主/master分支中。其次,核心开发者在审查讨论中略多于边缘开发者,且两组都关注可扩展性问题。第三,代理PR较少被修改,但当它们被修改时,两组通常进行重构。最后,边缘开发者更可能在不运行CI检查的情况下合并,而核心开发者更一致地在通过验证后才接受。我们的分析提供了开发者经验如何塑造整合的全面视角,为边缘和核心开发者如何有效与编码代理协作提供了见解。

英文摘要:

Autonomous AI agents are transforming software development and redefining how developers collaborate with AI. Prior research shows that the adoption and use of AI-powered tools differ between core and peripheral developers. However, it remains unclear how this dynamic unfolds in the emerging era of autonomous coding agents. In this paper, we present the first empirical study of 9,427 agentic PRs, examining how core and peripheral developers use, review, modify, and verify agent-generated contributions prior to acceptance. Through a mix of qualitative and quantitative analysis, we make four key contributions. First, a subset of peripheral developers use agents more often, delegating tasks evenly across bug fixing, feature addition, documentation, and testing. In contrast, core developers focus more on documentation and testing, yet their agentic PRs are frequently merged into the main/master branch. Second, core developers engage slightly more in review discussions than peripheral developers, and both groups focus on evolvability issues. Third, agentic PRs are less likely to be modified, but when they are, both groups commonly perform refactoring. Finally, peripheral developers are more likely to merge without running CI checks, whereas core developers more consistently require passing verification before acceptance. Our analysis offers a comprehensive view of how developer experience shapes integration offer insights for both peripheral and core developers on how to effectively collaborate with coding agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑