Deep Learning-Based Automated Test Case Generation from Natural Language Requirements
Keywords:
Automated test case generation, Boundary value analysis, Deep learning, Natural language processing, Requirement traceability, Semantic role labeling, Software requirements engineeringAbstract
Acceptance testing and system-level validation are essential yet resource-intensive and error-prone activities in software development, particularly for safety-critical and large-scale systems whose requirements are expressed in natural language. Manually deriving test cases from such requirements is time-consuming and difficult to scale as software specifications evolve. This review examines current approaches to automated test case generation from natural language requirements, with particular emphasis on Natural Language Processing (NLP)-based techniques for generating system-level acceptance tests from structured use-case specifications. These approaches integrate Semantic Role Labeling, semantic similarity techniques based on VerbNet and WordNet, Object Constraint Language (OCL) generation, and alloy-based constraint solving to transform textual requirements into executable test cases. Building on the strengths and limitations of rule-based NLP pipelines, the review also examines complementary approaches based on machine learning, deep learning, and Large Language Models (LLMs). Furthermore, the proposed project explores the potential of learned language representations to replace or augment manually engineered linguistic rules. This approach aims to improve generalizability, reduce manual configuration requirements, and enhance the ability to process diverse, complex, and unrestricted real-world software requirements.
References
C. Wang, F. Pastore, A. Goknil and L. C. Briand, “Automatic generation of acceptance test cases from use case specifications: An NLP-based approach,” in IEEE Transactions on Software Engineering, vol. 48, no. 2, pp. 585–616, Feb. 2022.
M. Zhang, T. Yue, S. Ali, H. Zhang, and J. Wu, “A systematic approach to automatically derive test cases from use cases specified in restricted natural languages,” System Analysis and Modeling: Models and Reusability, 2014, pp. 142–157.
E. Sarmiento, J. C. Leite, E. Almentero, and G. S. Alzamora, “Test scenario generation from natural language requirements descriptions based on Petri-Nets,” Electronic Notes in Theoretical Computer Science, vol. 329, pp. 123–148, Dec. 2016.
G. Carvalho et al., “NAT2TESTSCR: Test case generation from natural language requirements based on SCR specifications,” Science of Computer Programming, vol. 95, pp. 275–297, Dec. 2014.
O. Folorunsho and H. Reza, “AI-driven test case generation from natural language requirements: A survey of techniques and research gaps,” arXiv, 2025.
W. Takerngsaksiri, R. Charakorn, C. Tantithamthavorn, and Y.-F. Li, “Pytester: Deep reinforcement learning for text-to-testcase generation,” Journal of Systems and Software, vol. 224, Jun. 2025.
O. Karmouda, M. Ghaouat, and G. Feuilloley, “Automated test case generation from natural language requirements using large language models,” Proceedings of the Future Technologies Conference, Oct. 2025, pp. 260–281.
B. R. Korraprolu, P. Pinninti, and Y. R. Reddy, “Test case generation for requirements in natural language - An LLM comparison study,” Proceedings of the 18th Innovations in Software Engineering Conference, Apr. 2025, pp. 1–5.
Z. Xue et al., “Domain knowledge is all you need: A field deployment of LLM-powered test case generation in fintech domain,” Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings, May 2024, pp. 314–315.
J. Navarro and R. Ibarra, “Automatic test case generation using natural language processing: A systematic mapping study,” Information and Software Technology, vol. 189, Jan. 2026.
F. D. Shadrach, D. Devasenapathy, R. Anitha, M. L. Kumar, and K. Siripuri, “Efficient deep learning framework for arecanut disease detection using graph neural network and Bat algorithm,” Scientific Reports, vol. 16, Apr. 2026.
N. Taylor and D. Devasenapathy, “Multi-prototype face and body integration for automated attendance tracking in educational settings,” 2026 International Conference on Cognitive Computing and Networking Systems (ICC-CNS), Guntur, India, 2026, pp. 621–628.
D. Devasenapathy, K. Siripuri, J. Velusamy and R. Poonkodi, “Faster Region-based Convolutional Neural Network (R-CNN) for efficient object detection in Satellite Imagery,” 2026 International Conference on Cognitive Computing and Networking Systems (ICC-CNS), Guntur, India, 2026, pp. 683–689.
D. Devasenapathy, K. Bhimaavarapu, P. K. Sholapurapu, and S. Sarupriya, “Real-time classroom emotion analysis using machine and deep learning for enhanced student learning,” Journal of Intelligent Systems and Internet of Things, vol. 16, no. 2, pp. 82–101, 2025.
D. Devasenapathy, P. Madhumathy, R. Umamaheshwari, B. K. Pandey, and D. Pandey, “Transmission-efficient grid-based synchronized model for routing in wireless sensor networks using bayesian compressive sensing,” SN Computer Science/SN computer science, vol. 5, no. 1, Dec. 2023.
