arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.03556cs.SE
收藏

自主代理是否贡献测试代码?对代理拉取请求中测试的调查

Do Autonomous Agents Contribute Test Code? A Study of Tests in Agentic Pull Requests

University of Texas at Arlington(阿灵顿得克萨斯大学)

Sabrina Haque, Sarvesh Ingale, Christoph Csallner

AI总结:

研究分析了代理拉取请求中测试代码的出现频率及影响因素,揭示了测试代码对PR规模和处理时间的影响,为自主软件开发研究提供实证依据。

摘要:

测试是确保软件正确性和长期可维护性的关键实践。随着代理编码工具越来越多地提交拉取请求(PRs),了解测试在这些代理驱动的工作流中如何出现变得至关重要。使用AIDev数据集,我们对代理拉取请求中的测试包含情况进行了实证研究。我们检验了测试出现的频率、在PR生命周期中何时引入,以及包含测试的PR在大小、处理时间及合并结果上如何不同于不包含测试的PR。在不同代理中,包含测试的PR随时间推移更为常见,且通常更大、完成时间更长,而合并率总体上保持相似。我们还观察到不同代理在测试采用率以及测试PR中测试代码与生产代码之间的平衡上存在差异。我们的发现为代理拉取请求中的测试行为提供了描述性观点,并为未来自主软件开发研究提供了实证基础。

英文摘要:

Testing is a critical practice for ensuring software correctness and long-term maintainability. As agentic coding tools increasingly submit pull requests (PRs), it becomes essential to understand how testing appears in these agent-driven workflows. Using the AIDev dataset, we present an empirical study of test inclusion in agentic pull requests. We examine how often tests are included, when they are introduced during the PR lifecycle and how test-containing PRs differ from non-test PRs in terms of size, turnaround time, and merge outcomes. Across agents, test-containing PRs are more common over time and tend to be larger and take longer to complete, while merge rates remain largely similar. We also observe variation across agents in both test adoption and the balance between test and production code within test PRs. Our findings provide a descriptive view of testing behavior in agentic pull requests and offer empirical grounding for future studies of autonomous software development.

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。

↑