Academic Journal
Automated Update of Android Deprecated API Usages With Large Language Models
| Title: | Automated Update of Android Deprecated API Usages With Large Language Models |
|---|---|
| Authors: | Tarek Mahmud, Bin Duan, Meiru Che, Awatif Yasmin, Anne H. H. Ngu, Guowei Yang 0001 |
| Source: | IEEE Transactions on Software Engineering. 52:70-85 |
| Publication Status: | Preprint |
| Publisher Information: | Institute of Electrical and Electronics Engineers (IEEE), 2026. |
| Publication Year: | 2026 |
| Subject Terms: | 1712 Software, Large Language Model, Software Engineering (cs.SE), FOS: Computer and information sciences, Computer Science - Software Engineering, API Evolution, Android, GPT-4, Deprecated API, API Usage Update |
| Description: | 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. |
| Document Type: | Article |
| ISSN: | 2326-3881 0098-5589 |
| DOI: | 10.1109/tse.2025.3627897 |
| DOI: | 10.48550/arxiv.2411.04387 |
| Access URL: | http://arxiv.org/abs/2411.04387 https://espace.library.uq.edu.au/view/UQ:a9420df https://api.library.uq.edu.au/view/UQ:a9420df |
| Rights: | IEEE Copyright arXiv Non-Exclusive Distribution |
| Accession Number: | edsair.doi.dedup.....9db5941f9f0b937b4819ee017cb1924b |
| Database: | OpenAIRE |
| ISSN: | 23263881 00985589 |
|---|---|
| DOI: | 10.1109/tse.2025.3627897 |