关于代理编码的应用：GitHub上拉取请求的实证研究

摘要

大型语言模型（LLMs）正日益融入软件开发流程。通过使用自主AI代理，以最小化人工干预的方式生成代码并提交拉取请求，有望成为标准实践。然而，关于这些拉取请求的实际效用及其在现实项目中的接受程度，目前知之甚少。本文中，我们实证研究了使用Claude Code这一代理编码工具生成的567个GitHub拉取请求（PRs），这些请求分布于157个多样化的开源项目中。我们的分析显示，开发者倾向于依赖代理完成诸如重构、文档编写和测试等任务。结果表明，83.8%的代理辅助PRs最终被项目维护者接受并合并，其中54.9%的合并PRs未经进一步修改即被集成。剩余的45.1%则需要额外修改，特别是针对错误修复、文档完善及遵循项目特定标准等方面，这些修改得益于人工审阅。这些发现表明，尽管代理辅助的PRs大体上可被接受，但仍需人类监督与精炼以提升其质量。

English

Large language models (LLMs) are increasingly being integrated into software development processes. The ability to generate code and submit pull requests with minimal human intervention, through the use of autonomous AI agents, is poised to become a standard practice. However, little is known about the practical usefulness of these pull requests and the extent to which their contributions are accepted in real-world projects. In this paper, we empirically study 567 GitHub pull requests (PRs) generated using Claude Code, an agentic coding tool, across 157 diverse open-source projects. Our analysis reveals that developers tend to rely on agents for tasks such as refactoring, documentation, and testing. The results indicate that 83.8% of these agent-assisted PRs are eventually accepted and merged by project maintainers, with 54.9% of the merged PRs are integrated without further modification. The remaining 45.1% require additional changes benefit from human revisions, especially for bug fixes, documentation, and adherence to project-specific standards. These findings suggest that while agent-assisted PRs are largely acceptable, they still benefit from human oversight and refinement.

关于代理编码的应用：GitHub上拉取请求的实证研究

On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub

摘要

Support