Integrating Reinforcement Learning in Software Testing Automation: A Promising Approach

• Diogo Florencio de Lima UFCG
• Danyllo Albuquerque UFCG
• Emanuel Dantas Filho IFPB
• Mirko Perkusich UFCG
• Angelo Perkusich UFCG

DOI: https://doi.org/10.5753/ise.2023.235976

Resumo

In the rapidly evolving landscape of software development, ensuring reliable and efficient software systems is essential. However, traditional software testing methods often struggle to achieve comprehensive test coverage and adaptability to changing software dynamics. To address these challenges, this paper proposes an innovative approach that integrates reinforcement learning techniques into software testing automation. Our goal is to enhance test generation and prioritization strategies, leading to improved fault detection, adaptability, and resource utilization. By developing an intelligent testing framework that learns from feedback received during the testing process, we optimize test coverage and fault detection using reinforcement learning. Initial experiments demonstrate the potential of our approach in improving software testing outcomes. The integration of reinforcement learning into software testing automation holds promise for advancing the field, enabling more reliable and adaptable software systems, and reducing development costs.

Palavras-chave: Integrating, Reinforcement Learning, Software Testing Automation, Test Generation, Fault Detection

Referências

L. Chen, Y. Zhang, and X. Wang. 2023. Machine learning-based defect prediction in software systems. Journal of Software Engineering Research and Development 5, 1 (2023).

Xuan Chen, Yan Zhang, Wenbo Liu, Rui Yang, and Ming Zhang. 2022. Reinforcement Learning for Software Testing: A Survey. IEEE Transactions on Software Engineering (2022). https://doi.org/10.1109/TSE.2022.3175000

Yiran Huang, Xiaoqiang Wang, Jing Zhang, and Rui Yang. 2020. Reinforcement learning based test case prioritization for mobile software. In 2020 IEEE 42nd International Conference on Software Engineering (ICSE). IEEE, 975–986.

S. Lee, J. Kim, and S. Kim. 2023. Dynamic test generation for web applications using symbolic execution. In Proceedings of the International Symposium on Software Testing and Analysis (ISSTA).

Wenbo Liu, Yan Zhang, Ming Zhang, and Rui Yang. 2020. Reinforcement Learning for Software Testing: A Promising Approach. arXiv preprint arXiv:2004.07961 (2020).

J. Smith, D. Jones, and M. Brown. 2023. Automated test case generation using genetic algorithms. In Proceedings of the International Conference on Software Engineering (ICSE).

Y.Wang,W. Ding, and Y. Chen. 2023. Data mining techniques for software defect prediction: A comparative study. IEEE Transactions on Software Engineering 49, 2 (2023).

Yuan Xu, Yan Zhang, Rui Yang, Ming Zhang, and Wenbo Liu. 2020. A survey on reinforcement learning for software testing. arXiv preprint arXiv:2004.01461 (2020).

Q. Zhang, Y. Yang, and H. Mei. 2023. Evolutionary testing for adaptive systems: A review. Comput. Surveys 55, 4 (2023).

Yan Zhang, Rui Yang, Ming Zhang, and Wenbo Liu. 2021. Reinforcement Learning for Software Testing: A Survey and Research Directions. arXiv preprint arXiv:2104.00560 (2021).

Yan Zhang, Rui Yang, Ming Zhang, and Wenbo Liu. 2022. Reinforcement Learning for Software Testing: A Survey and Future Directions. ACM Transactions on Software Engineering and Methodology (TOSEM) (2022). https://doi.org/10.1145/3541201

Yan Zhang, Ming Zhang, Wenbo Liu, and Rui Yang. 2019. Reinforcement Learning for Software Testing: A Preliminary Study. In 2019 IEEE 26th International Conference on Software Analysis, Evolution, and Reengineering (SANER). IEEE, 35–44.