Library
Repository Home account_circle Login

Investigating Autonomous Agent Contributions in the Wild

Activity Patterns and Code Change over Time

Conference Paper (2026)
Author(s)

Razvan Mihai Popescu (TU Delft - Electrical Engineering, Mathematics and Computer Science)

David Gros (University of California)

Andrei Botocan (Student TU Delft)

Rahul Pandita (GitHub, Inc.)

Prem Devanbu (University of California)

Maliheh Izadi (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Research Group
Software Engineering
DOI related publication
https://doi.org/10.1145/3793302.3793354 Final published version
More Info
expand_more
Publication Year
2026
Language
English
Research Group
Software Engineering
Pages (from-to)
236-248
Publisher
ACM
ISBN (electronic)
9798400724749
Event
23rd International Conference on Mining Software Repositories, MSR 2026 (2026-04-13 - 2026-04-14), Rio de Janeiro, Brazil
Page Views
55
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The rise of large language models for code has reshaped software development. Autonomous coding agents, able to create branches, open pull requests, and perform code reviews, now actively contribute to real-world projects. Their growing role offers a unique and timely opportunity to investigate AI-driven contributions and their effects on code quality, team dynamics, and software maintainability. In this work, we construct a novel dataset of approximately 110,000 open-source pull requests, including associated commits, comments, reviews, issues, and file changes, collectively representing millions of lines of source code. We compare five popular coding agents, including OpenAI Codex, Claude Code, GitHub Copilot, Google Jules, and Devin, examining how their usage differs in various development aspects such as merge frequency, edited file types, and developer interaction signals, including comments and reviews. Furthermore, we emphasize that code authoring and review are only a small part of the larger software engineering process, as the resulting code must also be maintained and updated over time. Hence, we offer several longitudinal estimates of survival and churn rates for agent-generated versus human-authored code. Ultimately, our findings indicate an increasing agent activity in open-source projects, although their contributions are associated with more churn over time compared to human-authored code.