On the Adoption of AI Coding Agents in Open-source Android and iOS Development

TL;DR

This study empirically examines how AI coding agents contribute to open-source Android and iOS projects, revealing differences in acceptance rates, task success, and evolution over time, thus providing foundational insights into AI's role in mobile development.

Contribution

First empirical analysis of AI-generated code in open-source mobile projects, comparing Android and iOS, and establishing baseline metrics for agent contributions.

Findings

Android projects received twice as many AI-authored PRs as iOS.

PR acceptance rate is higher in Android (71%) than iOS (63%).

Routine tasks have higher success rates, while structural changes are less successful.

Abstract

AI coding agents are increasingly contributing to software development, yet their impact on mobile development has received little empirical attention. In this paper, we present the first category-level empirical study of agent-generated code in open-source mobile app projects. We analyzed PR acceptance behaviors across mobile platforms, agents, and task categories using 2,901 AI-authored pull requests (PRs) in 193 verified Android and iOS open-source GitHub repositories in the AIDev dataset. We find that Android projects have received 2x more AI-authored PRs and have achieved higher PR acceptance rate (71%) than iOS (63%), with significant agent-level variation on Android. Across task categories, PRs with routine tasks (feature, fix, and ui) achieve the highest acceptance, while structural changes like refactor and build achieve lower success and longer resolution times. Furthermore, our evolution analysis shows improvement in PR resolution time on Android through mid-2025 before it declined again. Our findings offer the first evidence-based characterization of AI agents effects on OSS mobile projects and establish empirical baselines for evaluating agent-generated contributions to design platform aware agentic systems.