Reproduce “Generative AI in Software Testing: Current Trends and Future Directions” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tanish Singla, Qusay H. Mahmoud
Researchers from Ontario Tech University conducted a systematic literature review to analyze the current trends and future directions of Generative AI in software testing. The review categorizes existing applications, evaluates effectiveness, and outlines potentials and limitations, demonstrating how Generative AI enhances test case generation accuracy (70-90%) and reduces inaccuracies in bug reports by over 40%.
Key insights
- Generative AI, particularly Large Language Models (LLMs), exhibits substantial potential in software testing due to advanced language representation and contextual awareness, which can be optimized via fine-tuning and prompt engineering.
- Applications of Generative AI span diverse testing domains, including test case generation, oracle generation, test prioritization, and bug detection, yet gaps persist, notably in comprehensive test data generation.
- The integration of Generative AI introduces ethical concerns, algorithmic bias, high computational demands, and the 'black box' nature of some models, necessitating careful consideration for responsible implementation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.