International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI-Based Automatic Generation of Software Test Cases |
|---|---|
| ABSTRACT | Software testing is essential for checking whether a software product behaves according to its requirements and for identifying defects before release. Test cases are commonly prepared from requirement documents, user stories, use cases and acceptance criteria. Manual test design can be time-consuming and may overlook boundary conditions, invalid inputs, role-based permissions or exception scenarios, particularly when requirements change frequently. Artificial intelligence (AI), natural language processing (NLP) and large language models (LLMs) can assist by converting natural-language requirements into structured candidate test cases. This paper reviews AI-assisted test-case generation and proposes a human-supervised framework that includes requirement analysis, generation, validation, deduplication, traceability and reviewer approval. The paper is conceptual: it does not report a deployed prototype, a trained model or experimental performance results. It discusses possible benefits, such as faster drafting and more systematic scenario exploration, together with risks including ambiguous specifications, unsupported assumptions, duplicate tests, privacy concerns and inaccurate expected outcomes. Generated cases should therefore be treated as drafts that require verification against authoritative requirements and, where possible, execution in the application under test. Future evaluation should compare AI-assisted and manual approaches using measures such as requirement coverage, validity, defect detection, duplication and reviewer effort. A descriptive questionnaire with 56 submitted responses is also summarised; the findings reflect respondent perceptions and are not a controlled evaluation of AI-generated test quality. |
| AUTHOR | ADINATH RAMESH GAWANDE, SHUBHANGI PRATIK BOMBLE Department of Master of Computer Applications, JCEI’s Jaihind Institute of Management and Research, Vadgaon, Sahani, India Assistant Professor, Department of Master of Computer Applications, JCEI’s Jaihind Institute of Management and Research, Vadgaon, Sahani, India |
| VOLUME | 189 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1410016 |
| pdf/16_AI-Based Automatic Generation of Software Test Cases.pdf | |
| KEYWORDS | |
| References |
[1] P. McMinn, “Search-based software test data generation: A survey,” Software Testing, Verification and Reliability, vol. 14, no. 2, pp. 105–156, 2004. doi: 10.1002/stvr.294. [2] A. Bertolino, “Software testing research: Achievements, challenges, dreams,” in Future of Software Engineering (FOSE '07), 2007, pp. 85–103. doi: 10.1109/FOSE.2007.25. [3] M. Utting, A. Pretschner, and B. Legeard, “A taxonomy of model-based testing approaches,” Software Testing, Verification and Reliability, vol. 22, no. 5, pp. 297–312, 2012. doi: 10.1002/stvr.456. [4] M. Harman, “The current state and future of search based software engineering,” in Future of Software Engineering, 2007, pp. 342–357. doi: 10.1109/FOSE.2007.29. [5] A. Fraser and A. Arcuri, “EvoSuite: Automatic test suite generation for object-oriented software,” in Proceedings of the 19th ACM SIGSOFT Symposium on the Foundations of Software Engineering, 2011, pp. 416–419. doi: 10.1145/2025113.2025179. [6] M. Utting and B. Legeard, Practical Model-Based Testing: A Tools Approach. San Francisco: Morgan Kaufmann, 2007. [7] ISO/IEC, ISO/IEC 25023:2016, Systems and Software Engineering—Systems and Software Quality Requirements and Evaluation (SQuaRE)—Measurement of System and Software Product Quality, 2016. [8] IEEE, IEEE Standard for Software and System Test Documentation, IEEE Std 829-2008, 2008. [9] A. Mesbah, A. van Deursen, and S. Lenselink, “Crawling Ajax-based web applications through dynamic analysis of user interface state changes,” ACM Transactions on the Web, vol. 6, no. 1, article 3, 2012. doi: 10.1145/2109205.2109208. [10] National Institute of Standards and Technology, Artificial Intelligence Risk Management Framework (AI RMF 1.0), NIST AI 100-1, 2023. doi: 10.6028/NIST.AI.100-1. [11] J. Wang, Y. Huang, C. Chen, Z. Liu, S. Wang, and Q. Wang, “Software Testing With Large Language Models: Survey, Landscape, and Vision,” IEEE Transactions on Software Engineering, vol. 50, no. 4, pp. 911–936, 2024, doi: 10.1109/TSE.2024.3368208. [12] M. Fontes, M. d’Amorim, and co-authors, “The integration of machine learning into automated test generation: A systematic mapping study,” Software Testing, Verification and Reliability, vol. 33, no. 4, e1845, 2023, doi: 10.1002/stvr.1845. [13] “Effective test generation using pre-trained Large Language Models and mutation testing,” Information and Software Technology, vol. 171, article 107468, 2024, doi: 10.1016/j.infsof.2024.107468. [14] M. Baqar and R. Khanda, “The Future of Software Testing: AI-Powered Test Case Generation and Validation,” arXiv:2409.05808, 2024. [15] Y. Chen et al., “A survey of unit test case generation methods,” Information and Software Technology, 2026 |