发表机构
Polytechnique Montréal（蒙特利尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究人工智能编码代理对软件开发的贡献，通过AIDev数据集，分析代理与人工生成PR的合并率差异、任务分布及关键特征，从实证和纵向角度理解其在软件开发中的作用、优点及局限性。
AI 中文摘要
大型语言模型的最新进展及其在软件工程任务中的迅速应用，使人工智能编码代理成为现代软件开发工作流程的一个组成部分。虽然开发人员越来越受益于这些编码代理，但其对软件质量的影响仍未得到充分理解。特别是，代理贡献在软件开发生命周期中的演变尚未得到充分研究。本研究旨在将代理拉取请求（PR）与人工生成的PR进行比较，并研究其属性在开发生命周期不同阶段如何变化。利用AIDev数据集，首先分析代理生成和人工生成的PR之间合并率的差异如何随时间变化。然后确定主要应用人工智能编码代理的开发任务类型，并研究这些任务分布如何在不同开发季度演变。最后，比较代理生成和人工生成的PR的一组关键特征，重点关注它们对软件质量的影响及其时间动态。总的来说，我们的发现为人工智能编码代理在软件开发中的作用提供了实证和纵向视角，更细致地理解了它们在实际应用中的优点和局限性。
英文摘要
Recent advances in large language models and their rapid adoption across software engineering tasks have made Artificial Intelligence (AI) coding agents an integral component of modern software development workflows. While developers increasingly benefit from these coding agents, their impact on software quality remains insufficiently understood. In particular, how agentic contributions evolve across the software development lifecycle has not been thoroughly investigated. This study aims to characterize agentic pull requests (PR) in comparison to human generated PRs and to examine how their properties change across different stages of the development lifecycle. Using the AIDev dataset, we first analyze how differences in merge rates between agentic and human generated PRs vary over time. We then identify the types of development tasks where AI coding agents are predominantly applied and investigate how these task distributions evolve across development quarters. Finally, we compare a set of key characteristics of agentic and human generated PRs, focusing on their implications for software quality and their temporal dynamics. Overall, our findings provide an empirical and longitudinal perspective on the role of AI coding agents in software development, offering a more nuanced understanding of their benefits and limitations in real-world practices.
