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

2026-02-12

AI Summary

This study addresses the lack of systematic empirical investigation into the real-world impact of AI-powered coding agents in open-source mobile application development. It presents the first category-level empirical analysis in this domain, leveraging the AIDev dataset to quantitatively evaluate 2,901 AI-generated pull requests (PRs) across 193 open-source Android and iOS projects. The work examines how platform, agent type, and task category influence PR acceptance rates and processing duration. Findings reveal that Android projects receive twice as many AI-generated PRs as iOS projects and exhibit a higher acceptance rate (71% vs. 63%). Routine tasks—such as feature implementation, bug fixes, and UI adjustments—achieve significantly higher success rates than structural changes. Additionally, Android PR processing efficiency showed a notable but transient improvement around mid-2025. This research establishes a benchmark for evaluating AI contributions and highlights the critical roles of platform and task type in shaping AI collaboration effectiveness.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Other Foundations of Human Computation & AI
• Intelligent Robots: Embodied AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• AI coding agents
• mobile development
• open-source software
• pull request acceptance
• empirical study

Innovation

• AI coding agents
• mobile development
• empirical study
• pull request acceptance
• platform-aware agentic systems