On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub
Об использовании агентного программирования: эмпирическое исследование запросов на включение изменений на GitHub
2026-03-06
SCID: 54.1/qfb5vc8g
Discuss with AI
Claude CodeGitHub pull requestsagentic codingautonomous AI agentsopen source projects
Figures from the paper
Abstract (AI)
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 article, 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 being integrated without further modification. The remaining 45.1% require additional changes and 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.
Key Findings
1
Among merged pull requests, 54.9% are integrated without modification, while 45.1% require additional changes.
2
Developers primarily use agentic coding tools for refactoring, documentation, and testing tasks.
3
Human revision is particularly beneficial for bug fixes, documentation, and adherence to project-specific standards, indicating that oversight remains important.
4
Project maintainers eventually accept and merge 83.8% of agent-assisted pull requests.
5
The study analyzes 567 pull requests generated with Claude Code across 157 diverse open-source GitHub projects.
Research Object
GitHub pull requests generated using Claude Code across open source projects
Research Subject
The acceptance, merging, modification requirements, and task distribution of agent-assisted pull requests
Publication Details
Publication Date
2026-03-06
Journal
Publisher
ISSN
Cited by
116
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest