Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

Early Adoption of Agentic Coding Tools by GitHub Projects

Source

arXiv

arxiv.org/abs/2607.14037v1

Read the source

Source

Plain-Language Brief

This research investigates the adoption and management of agentic coding tools in software development on GitHub. The study analyzes 25,264 agentic pull requests from 2,361 popular repositories to understand (1) how these tools are adopted, (2) project-level productivity, and (3) human-agent collaboration patterns. The findings show that intensive adoption is concentrated in a small subset of projects, with smaller projects exhibiting higher participation ratios. Project-level agentic PR productivity varies widely, and a single-human oversight model dominates human-agent collaboration.

What the Document Says

  • The study examines the use of agentic coding tools that generate and submit pull requests in software development on GitHub.
  • The research analyzes data from 25,264 agentic pull requests across 2,361 popular repositories to investigate adoption patterns, productivity, and human-agent collaboration.
  • Small projects (1-5 contributors) exhibit higher participation ratios and average levels of agentic PR activity than larger projects.
  • Project-level agentic PR productivity varies significantly. Some projects exceed an estimated 36 PRs per participant during the three-month observation period, while most remain below this threshold.
  • The study finds that human-agent collaboration is primarily characterized by a single-human oversight model, where one developer reviews or modifies the agent's contributions. Multi-human collaboration patterns are uncommon.

Key Concepts Mentioned

  • Agentic coding tools
  • Pull requests (PRs)
  • Software development
  • GitHub projects
  • Human-agent collaboration

Claims Made by the Document

  • Intensive adoption of agentic coding tools is concentrated in a small subset of projects.
  • Smaller projects exhibit higher participation ratios and average levels of agentic PR activity.
  • Project-level agentic PR productivity varies significantly.

Evidence Used

  • Analysis of 25,264 agentic pull requests from 2,361 popular GitHub repositories.

Methods / Approach

  • Data analysis of agentic pull requests from GitHub projects

Limitations Stated by the Authors

  • This study captures an early snapshot of agent adoption and may not reflect long-term trends.

Limitations Noted by the Agent

Agent interpretation — not from the source.

  • The study does not examine the factors driving the concentration of intensive adoption in a small subset of projects.
  • The research does not explore potential implications for software quality or project success as a result of increased use of agentic coding tools.

Open Questions

  • What factors contribute to the concentration of intensive agent adoption in a small subset of projects?
  • How does increased use of agentic coding tools impact software quality or project success?

Notes for Future Q&A

May include interpretation. Labeled where it does.

  • The study focuses on open-source projects, and it's unknown if the findings apply to other types of software development.
  • The research does not discuss the specific tools or techniques used by the agents.

Raw Abstract / Excerpt

Agentic coding tools are increasingly capable of generating and submitting pull requests (PRs) to software projects, introducing new forms of human-agent collaboration in software development. While prior studies have examined PR-level outcomes of agent-generated contributions, less is known about how agentic coding tools are adopted and managed at the project level. In this paper, we analyze 25,264 agentic PRs from 2,361 popular GitHub repositories to investigate (1) the adoption of agentic coding tools, (2) project-level agentic PR productivity, and (3) human-agent collaboration patterns. Our results show that the median repository generates only one to two agentic PRs during a three-month period, indicating that intensive adoption remains concentrated in a small subset of projects. At the same time, small projects (1-5 contributors) exhibit higher participation ratios and average levels of agentic PR activity than medium-sized and large projects. We also observe substantial variation in project-level agentic PR productivity. While a small number of projects exceed an industry-reported estimate of 36 PRs per participant during the three-month observation period, most projects remain below this threshold. Finally, human-agent collaboration is dominated by a single-human oversight model, in which one developer reviews and/or modifies the agent's contributions, while multi-human collaboration patterns remain uncommon. These findings provide early empirical evidence on how open-source projects organize human oversight around agentic coding tools and suggest that successful integration of agent-generated contributions depends not only on advances in agent capabilities but also on the human and organizational processes that govern their use. Because this study captures an early snapshot of agent adoption, future work should continue to track how adoption patterns evolve over time.