Automated Functional Testing for Malleable Mobile Application Driven from User Intent

TL;DR

This paper introduces ALADDIN, a framework that uses LLM-guided test generation to verify user-specified functionalities in malleable mobile apps, enabling end-user-driven app customization.

Contribution

The work presents a novel LLM-based test generation approach for verifying user-driven app functionalities, addressing a key challenge in malleable mobile applications.

Findings

ALADDIN effectively validates user-requested features in mobile apps.

The benchmark demonstrates ALADDIN's ability to detect both correct and faulty functionalities.

ALADDIN is practical for deployment in real-world scenarios.

Abstract

Software malleability allows applications to be easily changed, configured, and adapted even after deployment. While prior work has explored configurable systems, adaptive recommender systems, and malleable GUIs, these approaches are often tailored to specific software and lack generalizability. In this work, we envision per-user malleable mobile applications, where end-users can specify requirements that are automatically implemented via LLM-based code generation. However, realizing this vision requires overcoming the key challenge of designing automated test generation that can reliably verify both the presence and correctness of user-specified functionalities. We propose ALADDIN, a user-requirement-driven GUI test generation framework that incrementally navigates the UI, triggers desired functionalities, and constructs LLM-guided oracles to validate correctness. We build a benchmark spanning six popular mobile applications with both correct and faulty user-requested functionalities, demonstrating that ALADDIN effectively validates per-user features and is practical for real-world deployment. Our work highlights the feasibility of shifting mobile app development from a product-manager-driven to an end-user-driven paradigm.