Are We All Using Agents the Same Way? An Empirical Study of Core and Peripheral Developers Use of Coding Agents

2026-01-27

AI Summary

This study investigates behavioral differences between core and peripheral developers in their use of autonomous code-generating agents and the resulting impact on collaboration efficiency and code quality. Analyzing 9,427 agent-generated pull requests through large-scale data analysis, content coding, and statistical modeling, the research systematically reveals significant disparities in usage strategies, code review focus, and validation behaviors. Peripheral developers employ agents more frequently and evenly across tasks, whereas core developers concentrate on documentation and testing, yielding contributions more likely to be merged into the main codebase. Both groups seldom modify agent-generated code, yet peripheral developers are notably more prone to bypass continuous integration (CI) validation. These findings offer critical empirical insights into human–agent collaboration in software development.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Autonomous AI agents are transforming software development and redefining how developers collaborate with AI. Prior research shows that the adoption and use of AI-powered tools differ between core and peripheral developers. However, it remains unclear how this dynamic unfolds in the emerging era of autonomous coding agents. In this paper, we present the first empirical study of 9,427 agentic PRs, examining how core and peripheral developers use, review, modify, and verify agent-generated contributions prior to acceptance. Through a mix of qualitative and quantitative analysis, we make four key contributions. First, a subset of peripheral developers use agents more often, delegating tasks evenly across bug fixing, feature addition, documentation, and testing. In contrast, core developers focus more on documentation and testing, yet their agentic PRs are frequently merged into the main/master branch. Second, core developers engage slightly more in review discussions than peripheral developers, and both groups focus on evolvability issues. Third, agentic PRs are less likely to be modified, but when they are, both groups commonly perform refactoring. Finally, peripheral developers are more likely to merge without running CI checks, whereas core developers more consistently require passing verification before acceptance. Our analysis offers a comprehensive view of how developer experience shapes integration offer insights for both peripheral and core developers on how to effectively collaborate with coding agents.

Problem

• autonomous coding agents
• core developers
• peripheral developers
• code contribution
• developer collaboration

Innovation

• autonomous coding agents
• core vs. peripheral developers
• empirical study
• agentic pull requests
• AI-assisted software development