Automated Update of Android Deprecated API Usages with Large Language Models

TL;DR

This paper presents GUPPY, an automated system using GPT-4 to update deprecated Android API usages, generate tests, and refine updates, improving compatibility and reducing manual effort.

Contribution

GUPPY is the first approach leveraging large language models for automated deprecated API updates in Android apps, combining prompt engineering with iterative refinement.

Findings

GUPPY outperforms existing techniques in updating deprecated APIs.

GUPPY successfully updates 360 benchmark API usages and 156 from latest API levels.

The approach ensures compatibility and reduces manual effort in API maintenance.

Abstract

Android apps rely on application programming interfaces (APIs) to access various functionalities of Android devices. These APIs however are regularly updated to incorporate new features while the old APIs get deprecated. Even though the importance of updating deprecated API usages with the recommended replacement APIs has been widely recognized, it is non-trivial to update the deprecated API usages. Therefore, the usages of deprecated APIs linger in Android apps and cause compatibility issues in practice. This paper introduces GUPPY, an automated approach that utilizes large language models (LLMs) to update Android deprecated API usages. By employing carefully crafted prompts, GUPPY leverages GPT-4, one of the most powerful LLMs, to update deprecated-API usages, ensuring compatibility in both the old and new API levels. Additionally, GUPPY uses GPT-4 to generate tests, identify incorrect updates, and refine the API usage through an iterative process until the tests pass or a specified limit is reached. Our evaluation, conducted on 360 benchmark API usages from 20 deprecated APIs and an additional 156 deprecated API usages from the latest API levels 33 and 34, demonstrates GUPPY's advantages over the state-of-the-art techniques.