Automated Test Transfer Across Android Apps Using Large Language Models

2024-11-26

arXiv.org

AI Summary

To address the challenges of low reusability, poor cross-app migration success rates, and heavy reliance on manual assertion writing in Android inter-app UI testing, this paper introduces large language models (LLMs) to UI test migration for the first time, proposing an end-to-end automated migration method. Our approach integrates UI hierarchy analysis, element semantic understanding, prompt-engineering-driven script rewriting, and dynamic assertion generation to achieve functional semantic alignment and robust cross-application migration. Evaluated on a real-world application corpus, our method achieves a 97.5% migration success rate—outperforming the best baseline by 9.1 percentage points—while reducing manual effort by 91.1% and improving efficiency by 38.2%. The core contribution lies in overcoming the limitations of conventional layout- or widget-matching approaches under significant UI divergence and weak domain generalization, enabling semantic-level generalization and dynamic oracle generation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Application Domains: Mobility, Driving & Flight

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The pervasiveness of mobile apps in everyday life necessitates robust testing strategies to ensure quality and efficiency, especially through end-to-end usage-based tests for mobile apps' user interfaces (UIs). However, manually creating and maintaining such tests can be costly for developers. Since many apps share similar functionalities beneath diverse UIs, previous works have shown the possibility of transferring UI tests across different apps within the same domain, thereby eliminating the need for writing the tests manually. However, these methods have struggled to accommodate real-world variations, often facing limitations in scenarios where source and target apps are not very similar or fail to accurately transfer test oracles. This paper introduces an innovative technique, LLMigrate, which leverages Large Language Models (LLMs) to efficiently transfer usage-based UI tests across mobile apps. Our experimental evaluation shows LLMigrate can achieve a 97.5% success rate in automated test transfer, reducing the manual effort required to write tests from scratch by 91.1%. This represents an improvement of 9.1% in success rate and 38.2% in effort reduction compared to the best-performing prior technique, setting a new benchmark for automated test transfer.

Problem

• Automating UI test transfer across Android apps
• Reducing manual effort in test creation
• Handling real-world app variations effectively

Innovation

• Leverages LLMs for automated UI test transfer
• Achieves 97.5% success rate in test transfer
• Reduces manual test writing effort by 91.1%