BugRepro: Enhancing Android Bug Reproduction with Domain-Specific Knowledge Integration

TL;DR

BugRepro introduces a domain-specific knowledge integration method using retrieval-augmented generation and GUI analysis to improve Android bug reproduction accuracy and efficiency, outperforming existing approaches.

Contribution

It presents a novel technique combining retrieval-augmented generation and GUI exploration to enhance bug reproduction in complex Android apps, leveraging app-specific knowledge.

Findings

Significantly improves S2R entity extraction accuracy by up to 28.89 percentage points.

Achieves up to 152.63% higher bug reproduction success rate.

Enhances reproduction efficiency with up to 76.68% gains.

Abstract

Mobile application development is a fast-paced process where maintaining high-quality user experiences is crucial. Bug reproduction, a key aspect of maintaining app quality, often faces significant challenges. Specifically, when descriptions in bug reports are ambiguous or difficult to comprehend, current approaches fail to extract accurate information. Moreover, modern applications exhibit inherent complexity with multiple pages and diverse functionalities, making it challenging for existing methods to map the relevant information in bug reports to the corresponding UI elements that need to be manipulated. To address these challenges, we propose BugRepro, a novel technique that integrates domain-specific knowledge to enhance the accuracy and efficiency of bug reproduction. BugRepro adopts a Retrieval-Augmented Generation (RAG) approach. It retrieves similar bug reports along with their corresponding steps to reproduce (S2R) entities from an example-rich RAG document. In addition, BugRepro explores the graphical user interface (GUI) of the app and extracts transition graphs from the user interface to incorporate app-specific knowledge to guide large language models (LLMs) in their exploration process. Our experiments demonstrate that BugRepro significantly outperforms two state-of-the-art methods (ReCDroid and AdbGPT). For S2R entity extraction accuracy, it achieves a 7.57 to 28.89 percentage point increase over prior methods. For the bug reproduction success rate, the improvement reaches 74.55% and 152.63%. In reproduction efficiency, the gains are 0.72% and 76.68%.