A Pilot Study on LLM-Based Agentic Translation from Android to iOS: Pitfalls and Insights

TL;DR

This study evaluates the effectiveness of LLM-based agentic approaches for translating mobile applications from Android to iOS, highlighting key challenges, failure points, and proposing guidelines for improved cross-platform translation.

Contribution

It introduces a chain of agents that consider dependencies and program structure for Android to iOS translation and provides a detailed analysis of their performance and limitations.

Findings

Identified common failure modes in LLM-based translation.

Proposed guidelines to enhance translation accuracy.

Manual evaluation showed varying success in syntactic and semantic correctness.

Abstract

The rapid advancement of mobile applications has led to a significant demand for cross-platform compatibility, particularly between the Android and iOS platforms. Traditional approaches to mobile application translation often rely on manual intervention or rule-based systems, which are labor-intensive and time-consuming. While recent advancements in machine learning have introduced automated methods, they often lack contextual understanding and adaptability, resulting in suboptimal translations. Large Language Models (LLMs) were recently leveraged to enhance code translation at different granularities, including the method, class, and repository levels. Researchers have investigated common errors, limitations, and potential strategies to improve these tasks. However, LLM-based application translation across different platforms, such as migrating mobile applications between Android and iOS or adapting software across diverse frameworks, remains underexplored. Understanding the performance, strengths, and limitations of LLMs in cross-platform application translation is critical for advancing software engineering automation. This study aims to fill this gap by evaluating LLM-based agentic approaches for mobile application translation, identifying key failure points, and proposing guidelines to improve translation performance. We developed a chain of agents that account for dependencies, specifications, program structure, and program control flow when translating applications from Android to iOS. To evaluate the performance, we manually examined the translated code for syntactic correctness, semantic accuracy, and functional completeness. For translation failures, we further conducted a detailed root cause analysis to understand the underlying limitations of the agentic translation process and identify opportunities for improvement.