DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent Execution Traces Using LLMs to Detect Android Behavioural Code Smells

TL;DR

DynamicsLLM enhances Android behavioural code smell detection by leveraging LLMs to generate intelligent execution traces, significantly improving coverage over existing static and dynamic analysis tools.

Contribution

It introduces DynamicsLLM, a novel hybrid approach using LLMs to generate execution traces, improving detection coverage especially in apps with few activities.

Findings

DynamicsLLM with 100% LLM covers three times more code smell events than Dynamics.

The hybrid approach increases LLM coverage by 25.9% in apps with few activities.

12.7% of code smell events undetected by Dynamics are triggered by DynamicsLLM.

Abstract

Mobile apps have become essential of our daily lives, making code quality a critical concern for developers. Behavioural code smells are characteristics in the source code that induce inappropriate code behaviour during execution, which negatively impact software quality in terms of performance, energy consumption, and memory. Dynamics, the latest state-of-the-art tool-based method, is highly effective at detecting Android behavioural code smells. While it outperforms static analysis tools, it suffers from a high false negative rate, with multiple code smell instances remaining undetected. Large Language Models (LLMs) have achieved notable advances across numerous research domains and offer significant potential for generating intelligent execution traces, particularly for detecting behavioural code smells in Android mobile applications. By intelligent execution trace, we mean a sequence of events generated by specific actions in a way that triggers the identification of a given behaviour. We propose the following three main contributions in this paper: (1) DynamicsLLM, an enhanced implementation of the Dynamics method that leverages LLMs to intelligently generate execution traces. (2) A novel hybrid approach designed to improve the coverage of code smell-related events in applications with a small number of activities. (3) A comprehensive validation of DynamicsLLM on 333 mobile applications from F-DROID, including a comparison with the Dynamics tool. Our results show that, under a limited number of actions, DynamicsLLM configured with 100% LLM covers three times more code smell-related events than Dynamics. The hybrid approach improves LLM coverage by 25.9% for apps containing few activities. Moreover, 12.7% of the code smell-related events that cannot be triggered by Dynamics are successfully triggered by our tool.