{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T08:13:56Z","timestamp":1775808836862,"version":"3.50.1"},"reference-count":89,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T00:00:00Z","timestamp":1771632000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T00:00:00Z","timestamp":1771632000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Software Qual J"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s11219-026-09744-9","type":"journal-article","created":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T11:53:55Z","timestamp":1771674835000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated test plan generation using large language models"],"prefix":"10.1007","volume":"34","author":[{"given":"Susmita","family":"Haldar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luiz Fernando","family":"Capretz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,21]]},"reference":[{"key":"9744_CR1","doi-asserted-by":"crossref","unstructured":"Alagarsamy, S., Tantithamthavorn, C., Takerngsaksiri, W., Arora, C., & Aleti, A. (2025). Enhancing large language models for text-to-testcase generation. Journal of Systems and Software,230, 112531. https:\/\/doi.org\/10.1016\/j.jss.2025.112531. Retrieved from https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0164121225001992","DOI":"10.1016\/j.jss.2025.112531"},{"key":"9744_CR2","unstructured":"Apache Software Foundation (n.d.). Apache jmeter (performance testing tool). Available at: https:\/\/jmeter.apache.org\/."},{"key":"9744_CR3","unstructured":"Appium Contributors (2025). Appium documentation. Retrieved from https:\/\/appium.io\/docs\/en\/latest\/ (Accessed: 2026\u201301-26)."},{"key":"9744_CR4","unstructured":"Atlassian (2025). Jira software. Retrieved from https:\/\/www.atlassian.com\/software\/jira (Accessed: 2025\u201302-06)."},{"issue":"04","key":"9744_CR5","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MS.2006.113","volume":"23","author":"J Bach","year":"2006","unstructured":"Bach, J., Bertolino, A., Kaner, C., Glass, R. L., & Collard, R. (2006). Software Testing and Industry Needs. IEEE Software, 23(04), 55\u201357. https:\/\/doi.org\/10.1109\/MS.2006.113","journal-title":"IEEE Software"},{"key":"9744_CR6","doi-asserted-by":"crossref","unstructured":"Balsam, S., & Mishra, D. (2025). Web application testing-challenges and opportunities. Journal of Systems and Software,219, 112186. https:\/\/doi.org\/10.1016\/j.jss.2024.112186https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0164121224002309","DOI":"10.1016\/j.jss.2024.112186"},{"key":"9744_CR7","doi-asserted-by":"crossref","unstructured":"Belzner, L., Gabor, T., & Wirsing, M. (2024). Large language model assisted software engineering: Prospects, challenges, and a case study. B. Steffen (Ed.), Bridging the gap between ai and reality (pp. 355\u2013374). Cham: Springer Nature Switzerland.","DOI":"10.1007\/978-3-031-46002-9_23"},{"key":"9744_CR8","doi-asserted-by":"publisher","unstructured":"Beyo\u011flu, M. M., Kaya, E., & Karabulut, E. (2024). Assessment of the quality, readability, and usefulness of chatgpt generated medical information for ten common cancer types. Universal Access in the Information Society, pp. 1\u20137. https:\/\/doi.org\/10.1007\/s10209-024-01155-6.","DOI":"10.1007\/s10209-024-01155-6"},{"key":"9744_CR9","doi-asserted-by":"crossref","unstructured":"Bozic, J., & Wotawa, F. (2019). Software testing: According to plan! 2019 ieee international conference on software testing, verification and validation workshops (icstw) (p. 23\u201331).","DOI":"10.1109\/ICSTW.2019.00028"},{"key":"9744_CR10","doi-asserted-by":"crossref","unstructured":"Chan, C. K. Y., & Tsi, L. H. (2024). Will generative ai replace teachers in higher education? a study of teacher and student perceptions. Studies in Educational Evaluation,83, 101395. https:\/\/doi.org\/10.1016\/j.stueduc.2024.101395, Retrieved from https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0191491X24000749.","DOI":"10.1016\/j.stueduc.2024.101395"},{"key":"9744_CR11","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1038\/s41391-023-00705-y","volume":"27","author":"A Cocci","year":"2024","unstructured":"Cocci, A., Pezzoli, M., Re, M. L., et al. (2024). Quality of information and appropriateness of chatgpt outputs for urology patients. Prostate Cancer and Prostatic Diseases, 27, 103\u2013108. https:\/\/doi.org\/10.1038\/s41391-023-00705-y","journal-title":"Prostate Cancer and Prostatic Diseases"},{"key":"9744_CR12","unstructured":"Cohere AI (2025). Cohere: The all-in-one platform for private and secure ai. https:\/\/cohere.com\/. (Cohere provides cutting-edge multilingual models, advanced retrieval, and an AI workspace tailored for modern enterprises. Accessed: 2025\u201302-07)."},{"key":"9744_CR13","unstructured":"Cypress.io (2025). Test. automate. accelerate. Retrieved from https:\/\/www.cypress.io\/ (Accessed: 2025\u201302-06)."},{"key":"9744_CR14","doi-asserted-by":"crossref","unstructured":"Dakhel, A. M., Nikanjam, A., Majdinasab, V., Khomh, F., & Desmarais, M. C. (2024). Effective test generation using pre-trained large language models and mutation testing. Information and Software Technology,171, 107468. https:\/\/doi.org\/10.1016\/j.infsof.2024.107468, Retrieved from https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950584924000739.","DOI":"10.1016\/j.infsof.2024.107468"},{"key":"9744_CR15","doi-asserted-by":"crossref","unstructured":"Ferreira, M., Viegas, L., Faria, J.P., Lima, B. (2025). Acceptance Test Generation with Large Language Models: An Industrial Case Study. 2025 ieee\/acm international conference on automation of software test (ast) (p. 1\u201311). Los Alamitos, CA, USA: IEEE Computer Society. Retrieved from https:\/\/doi.ieeecomputersociety.org\/10.1109\/AST66626.2025.00007.","DOI":"10.1109\/AST66626.2025.00007"},{"issue":"3","key":"9744_CR16","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1037\/h0057532","volume":"32","author":"R Flesch","year":"1948","unstructured":"Flesch, R. (1948). A new readability yardstick. Journal of Applied Psychology, 32(3), 221\u2013233. https:\/\/doi.org\/10.1037\/h0057532","journal-title":"Journal of Applied Psychology"},{"key":"9744_CR17","doi-asserted-by":"publisher","unstructured":"Forg\u00e1cs, I., & Kov\u00e1cs, A. (2024). Modern software testing techniques: A practical guide for developers and testers (1st ed.). Berkeley, CA: Apress. Retrieved from https:\/\/doi.org\/10.1007\/978-1-4842-9893-0 (Softcover ISBN: 978-1-4842-9892-3, eBook ISBN: 978-1-4842-9893-0).","DOI":"10.1007\/978-1-4842-9893-0"},{"key":"9744_CR18","doi-asserted-by":"crossref","unstructured":"Gallegos, I. O., Rossi, R. A., Barrow, J., Tanjim, M. M., Kim, S., Dernoncourt, F., & Ahmed, N. K. (2024). Bias and fairness in large language models: A survey. Computational Linguistics,50(3), 1097\u20131179. https:\/\/doi.org\/10.1162\/coli_a_00524. Retrieved from https:\/\/aclanthology.org\/2024.cl-3.8\/","DOI":"10.1162\/coli_a_00524"},{"key":"9744_CR19","doi-asserted-by":"crossref","unstructured":"Garousi, V., Felderer, M., Kuhrmann, M., Herkilo\u011flu, K., Eldh, S. (2020). Exploring the industry\u2019s challenges in software testing: An empirical study. J. Softw. Evol. Process,32(8). Retrieved from https:\/\/doi.org\/10.1002\/smr.2251.","DOI":"10.1002\/smr.2251"},{"issue":"3","key":"9744_CR20","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1007\/s10664-015-9384-6","volume":"21","author":"J Grigera","year":"2016","unstructured":"Grigera, J., Garrido, A., Panach, J. I., Distante, D., & Rossi, G. (2016). Assessing refactorings for usability in e-commerce applications. Empirical Software Engineering, 21(3), 1224\u20131271. https:\/\/doi.org\/10.1007\/s10664-015-9384-6","journal-title":"Empirical Software Engineering"},{"key":"9744_CR21","unstructured":"Groq, Inc. (2025). Groq API Documentation. Retrieved from https:\/\/console.groq.com\/docs\/api-reference. (Accessed: 2025\u201302-08)."},{"key":"9744_CR22","volume-title":"The technique of clear writing","author":"R Gunning","year":"1952","unstructured":"Gunning, R. (1952). The technique of clear writing. McGraw-Hill."},{"key":"9744_CR23","unstructured":"Gurock Software GmbH (2024). Testrail (test case management tool). https:\/\/www.gurock.com\/testrail\/. (Accessed: 2024\u201310-01)."},{"key":"9744_CR24","unstructured":"Heusser, M., & Larsen, M. (2023). Software testing strategies: A testing guide for the 2020s. Packt Publishing Ltd."},{"key":"9744_CR25","doi-asserted-by":"publisher","DOI":"10.1002\/9781118602270","volume-title":"Fundamentals of software testing","author":"B Hom\u00e8s","year":"2012","unstructured":"Hom\u00e8s, B. (2012). Fundamentals of software testing. London, UK and Hoboken, NJ, USA: Wiley-ISTE."},{"key":"9744_CR26","unstructured":"IEEE Computer Society (2024). Guide to the software engineering body of knowledge (swebok) (4.0 ed.). Los Alamitos, CA, USA: IEEE Computer Society. Retrieved from https:\/\/www.computer.org\/education\/bodies-of-knowledge\/software-engineering (SWEBOK 4.0 reflects modern practices in software engineering, including Agile, DevOps, and continuous testing.)."},{"key":"9744_CR27","unstructured":"IEEE Standards Committee (1998). Ieee standard for software test documentation (Tech. Rep. No. IEEE 829\u20131998). IEEE. Retrieved from https:\/\/standards.ieee.org\/standard\/829-1998.html."},{"key":"9744_CR28","unstructured":"Institute of Electrical and Electronics Engineers (2008). IEEE Standard for Software and System Test Documentation (Tech. Rep. No. IEEE 829\u20132008). New York, NY, USA: IEEE. Retrieved from https:\/\/ieeexplore.ieee.org\/document\/4601587."},{"key":"9744_CR29","unstructured":"Institute of Electrical and Electronics Engineers (2013). ISO\/IEC\/IEEE International Standard 29119 Software Testing (Tech. Rep. No. ISO\/IEC\/IEEE 29119\u20131 to 29119\u20135). New York, NY, USA: IEEE Computer Society. Retrieved from https:\/\/ieeexplore.ieee.org\/document\/6506911."},{"key":"9744_CR30","unstructured":"International Organization for Standardization, International Electrotechnical Commission, IEEE. (2021). ISO\/IEC\/IEEE 29119\u20133:2021 - software and systems engineering - software testing - part 3: Test documentation. https:\/\/www.iso.org\/standard\/72255.html. (Second Edition, Accessed: 2025\u201306-07)."},{"key":"9744_CR31","unstructured":"International Software Testing Qualifications Board (2024a). Certified tester advanced level test management syllabus. Retrieved from https:\/\/istqb.org. (Accessed: 2026\u201301-27)."},{"key":"9744_CR32","unstructured":"International Software Testing Qualifications Board (2024b). https:\/\/www.istqb.org\/wp-content\/uploads\/2024\/11\/ISTQB_CTFL_Syllabus_v4.0.1.pdf (Accessed: 2025\u201302-28)."},{"key":"9744_CR33","unstructured":"International Software Testing Qualifications Board (2025). Certified tester specialist level syllabus \u2013 testing with generative ai (ct-genai), v1.0 (Tech. Rep.). ISTQB. Retrieved from https:\/\/www.istqb.org\/ (Version 1.0, Published 25 July 2025)."},{"key":"9744_CR34","doi-asserted-by":"crossref","unstructured":"Karmarkar, H., Agrawal, S., Chauhan, A., & Shete, P. (2024). Navigating confidentiality in test automation: A case study in llm driven test data generation. 2024 ieee international conference on software analysis, evolution and reengineering (saner) (p. 337\u2013348).","DOI":"10.1109\/SANER60148.2024.00041"},{"key":"9744_CR35","doi-asserted-by":"publisher","first-page":"58715","DOI":"10.1109\/ACCESS.2024.3391815","volume":"12","author":"S Karpurapu","year":"2024","unstructured":"Karpurapu, S., Myneni, S., Nettur, U., Gajja, L. S., Burke, D., Stiehm, T., & Payne, J. (2024). Comprehensive evaluation and insights into the use of large language models in the automation of behavior-driven development acceptance test formulation. IEEE Access, 12, 58715\u201358721. https:\/\/doi.org\/10.1109\/ACCESS.2024.3391815","journal-title":"IEEE Access"},{"key":"9744_CR36","unstructured":"Katalon (2025). Katalon is your all-in-one test automation solution. Retrieved from https:\/\/katalon.com\/ (Accessed: 2025\u201302-06)."},{"key":"9744_CR37","doi-asserted-by":"crossref","unstructured":"Kincaid, J.P., Fishburne, R.P.J., Rogers, R.L., & Chissom, B.S. (1975). Derivation of new readability formulas (automated readability index, fog count and flesch reading ease formula) for navy enlisted personnel (Tech. Rep. Nos. Research Branch Report 8\u201375). Millington, TN, USA: Naval Technical Training Command, Research Branch. Retrieved from https:\/\/stars.library.ucf.edu\/istlibrary\/56.","DOI":"10.21236\/ADA006655"},{"key":"9744_CR38","first-page":"22199","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2022). Large language models are zero-shot reasoners. Advances in neural information processing systems, 35, 22199\u201322213.","journal-title":"Advances in neural information processing systems"},{"issue":"3","key":"9744_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1360602.1361211","volume":"33","author":"DS Kushwaha","year":"2008","unstructured":"Kushwaha, D. S., & Misra, A. K. (2008). Software test effort estimation. ACM SIGSOFT Software Engineering Notes, 33(3), 1\u20135. https:\/\/doi.org\/10.1145\/1360602.1361211","journal-title":"ACM SIGSOFT Software Engineering Notes"},{"key":"9744_CR40","doi-asserted-by":"publisher","unstructured":"Leiser, F., Eckhardt, S., Leuthe, V., Knaeble, M., M\u00e4dche, A., Schwabe, G., & Sunyaev, A. (2024). Hill: A hallucination identifier for large language models. Proceedings of the 2024 chi conference on human factors in computing systems. New York, NY, USA: Association for Computing Machinery. Retrieved from https:\/\/doi.org\/10.1145\/3613904.3642428.","DOI":"10.1145\/3613904.3642428"},{"issue":"1","key":"9744_CR41","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s11219-023-09616-6","volume":"32","author":"M Leotta","year":"2024","unstructured":"Leotta, M., Paparella, D., & Ricca, F. (2024). Mutta: a novel tool for e2e web mutation testing. Software Quality Journal, 32(1), 5\u201326. https:\/\/doi.org\/10.1007\/s11219-023-09616-6","journal-title":"Software Quality Journal"},{"key":"9744_CR42","doi-asserted-by":"publisher","unstructured":"Li, T., Cui, C., Huang, R., Towey, D., & Ma, L. (2025). Large language models for automated web-form-test generation: An empirical study. ACM Trans. Softw. Eng. Methodol. https:\/\/doi.org\/10.1145\/3735553.","DOI":"10.1145\/3735553"},{"key":"9744_CR43","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, P., Wang, H., Chu, J., & Wong, W. E. (2025). Evaluating large language models for software testing. Computer Standards & Interfaces,93, 103942. https:\/\/doi.org\/10.1016\/j.csi.2024.103942, Retrieved from https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0920548924001119.","DOI":"10.1016\/j.csi.2024.103942"},{"key":"9744_CR44","doi-asserted-by":"crossref","unstructured":"Ling, Y., Yu, S., Fang, C., Pan, G., Wang, J., & Liu, J. (2025). Redefining crowdsourced test report prioritization: An innovative approach with large language model. Information and Software Technology,179, 107629. https:\/\/doi.org\/10.1016\/j.infsof.2024.107629, Retrieved from https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950584924002349.","DOI":"10.1016\/j.infsof.2024.107629"},{"key":"9744_CR45","first-page":"43136","volume":"36","author":"H Ma","year":"2023","unstructured":"Ma, H., Zhang, C., Bian, Y., Liu, L., Zhang, Z., Zhao, P., & Wu, B. (2023). Fairness-guided few-shot prompting for large language models. Advances in Neural Information Processing Systems, 36, 43136\u201343155.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"9744_CR46","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s10009-010-0177-3","volume":"13","author":"A Marchetto","year":"2011","unstructured":"Marchetto, A., Tiella, R., Tonella, P., Alshahwan, N., & Harman, M. (2011). Crawlability metrics for automated web testing. International Journal on Software Tools for Technology Transfer, 13(2), 131\u2013149. https:\/\/doi.org\/10.1007\/s10009-010-0177-3","journal-title":"International Journal on Software Tools for Technology Transfer"},{"key":"9744_CR47","unstructured":"Micro Focus (n.d.). Hp alm (application lifecycle management). Available at: https:\/\/www.microfocus.com\/en-us\/products\/application-lifecycle-management\/overview"},{"key":"9744_CR48","doi-asserted-by":"crossref","unstructured":"Milchevski, D., Frank, G., H\u00e4tty, A., Wang, B., Zhou, X., & Feng, Z. (2025). Multi-step generation of test specifications using large language models for system-level requirements. G. Rehm and Y. Li (Eds.), Proceedings of the 63rd annual meeting of the association for computational linguistics (volume 6: Industry track) (pp. 132\u2013146). Vienna, Austria: Association for Computational Linguistics. Retrieved from https:\/\/aclanthology.org\/2025.acl-industry.11\/.","DOI":"10.18653\/v1\/2025.acl-industry.11"},{"key":"9744_CR49","unstructured":"Mistral AI (2024). Mistral ai - frontier ai in your hands. Retrieved from https:\/\/mistral.ai\/en (Accessed: 2025\u201302-08)."},{"key":"9744_CR50","volume-title":"The art of software testing","author":"GJ Myers","year":"2011","unstructured":"Myers, G. J., Sandler, C., & Badgett, T. (2011). The art of software testing (3rd ed.). Hoboken, NJ: John Wiley & Sons.","edition":"3"},{"key":"9744_CR51","unstructured":"Nguyen, H.Q., Johnson, B., Hackett, M. (2003). Testing applications on the web: Test planning for mobile and internet-based systems (2nd ed.). Wiley."},{"key":"9744_CR52","doi-asserted-by":"crossref","unstructured":"Nguyen, V., Pham, V., & Lam, V. (2013). qestimation: a process for estimating size and effort of software testing. In Proceedings of the 2013 international conference on software and system process (icssp \u201913), (pp. 20\u201328). Association for Computing Machinery.","DOI":"10.1145\/2486046.2486052"},{"key":"9744_CR53","doi-asserted-by":"crossref","unstructured":"Nidagundi, P., & Novickis, L. (2017). New method for mobile application testing using lean canvas to improving the test strategy. In 2017 12th international scientific and technical conference on computer sciences and information technologies (csit), (Vol. 1, p. 171\u2013174).","DOI":"10.1109\/STC-CSIT.2017.8098761"},{"key":"9744_CR54","unstructured":"OpenAI (2024a). https:\/\/platform.openai.com\/docs\/ (Accessed: 2024\u201311-12)."},{"key":"9744_CR55","unstructured":"OpenAI (2024b). Retrieved from https:\/\/platform.openai.com\/docs\/models#gpt-4o (Accessed: 2025\u201302-08)."},{"key":"9744_CR56","unstructured":"OrangeHRM Team (2025). OrangeHRM: Human Resource Management System. Retrieved from https:\/\/github.com\/orangehrm\/orangehrm (Accessed: 2025\u201302-06)."},{"key":"9744_CR57","unstructured":"Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C.L., Mishkin, P. & Lowe, R. (2022). Training language models to follow instructions with human feedback. In Proceedings of the 36th international conference on neural information processing systems. Red Hook, NY, USA: Curran Associates Inc."},{"key":"9744_CR58","unstructured":"Paessler AG (n.d.). Paessler web server stress tool. https:\/\/www.paessler.com\/tools\/webstress. (Accessed: 2024\u201310-01)."},{"key":"9744_CR59","doi-asserted-by":"crossref","unstructured":"Patel, S., & Shah, V. (2015). Automated testing of software-as-a-service configurations using a variability language. In Proceedings of the 19th international conference on software product line, (p. 253\u2013262). New York, NY, USA: Association for Computing Machinery. Retrieved from https:\/\/doi.org\/10.1145\/2791060.2791072.","DOI":"10.1145\/2791060.2791072"},{"key":"9744_CR60","unstructured":"Pichai, S., & Hassabis, D. (2024). Our next-generation model: Gemini 1.5. https:\/\/blog.google\/technology\/ai\/google-gemini-next-generation-model-february-2024\/. (Accessed: 2025\u201310-17)."},{"key":"9744_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2024.107523","volume":"175","author":"C Pornprasit","year":"2024","unstructured":"Pornprasit, C., & Tantithamthavorn, C. (2024). Fine-tuning and prompt engineering for large language models-based code review automation. Information and Software Technology, 175, Article 107523.","journal-title":"Information and Software Technology"},{"key":"9744_CR62","unstructured":"Prompt Engineering Guide (2025). Prompt engineering guide. https:\/\/www.promptingguide.ai\/. (Accessed: 2025\u201302-22)."},{"issue":"4","key":"9744_CR63","doi-asserted-by":"publisher","first-page":"1104","DOI":"10.1109\/TSE.2025.3541166","volume":"51","author":"A Saboor Yaraghi","year":"2025","unstructured":"Saboor Yaraghi, A., Holden, D., Kahani, N., & Briand, L. (2025). Automated test case repair using language models. IEEE Transactions on Software Engineering, 51(4), 1104\u20131133. https:\/\/doi.org\/10.1109\/TSE.2025.3541166","journal-title":"IEEE Transactions on Software Engineering"},{"key":"9744_CR64","doi-asserted-by":"crossref","unstructured":"Santos, R., Santos, I., Magalhaes, C., & de Souza Santos, R. (2024). Are we testing or being tested? exploring the practical applications of large language models in software testing. In 2024 ieee conference on software testing, verification and validation (icst), (p. 353\u2013360).","DOI":"10.1109\/ICST60714.2024.00039"},{"issue":"1","key":"9744_CR65","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/TSE.2023.3334955","volume":"50","author":"M Sch\u00e4fer","year":"2024","unstructured":"Sch\u00e4fer, M., Nadi, S., Eghbali, A., & Tip, F. (2024). An empirical evaluation of using large language models for automated unit test generation. IEEE Transactions on Software Engineering, 50(1), 85\u2013105. https:\/\/doi.org\/10.1109\/TSE.2023.3334955","journal-title":"IEEE Transactions on Software Engineering"},{"key":"9744_CR66","unstructured":"Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C. others (2024). The prompt report: a systematic survey of prompt engineering techniques. arXiv:2406.06608."},{"issue":"12","key":"9744_CR67","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1109\/TSE.2015.2461542","volume":"41","author":"M Schur","year":"2015","unstructured":"Schur, M., Roth, A., & Zeller, A. (2015). Mining workflow models from web applications. IEEE Transactions on Software Engineering, 41(12), 1184\u20131201. https:\/\/doi.org\/10.1109\/TSE.2015.2461542","journal-title":"IEEE Transactions on Software Engineering"},{"key":"9744_CR68","unstructured":"Selenium Project (2024). Selenium (web browser automation tool) (Tech. Rep.). SeleniumHQ. Retrieved from https:\/\/www.selenium.dev\/ (Accessed: 2024\u201310-01)."},{"key":"9744_CR69","doi-asserted-by":"publisher","first-page":"169036","DOI":"10.1109\/ACCESS.2020.3022876","volume":"8","author":"N Setiani","year":"2020","unstructured":"Setiani, N., Ferdiana, R., & Hartanto, R. (2020). Test case understandability model. IEEE. Access, 8, 169036\u2013169046. https:\/\/doi.org\/10.1109\/ACCESS.2020.3022876","journal-title":"Access"},{"key":"9744_CR70","unstructured":"Spring Team (2025). Spring PetClinic. Retrieved from https:\/\/github.com\/spring-projects\/spring-petclinic (Accessed: 2025\u201302-06)."},{"key":"9744_CR71","doi-asserted-by":"crossref","unstructured":"Strandberg, P.E., Frasheri, M., & Enoiu, E.P. (2021). Ethical ai-powered regression test selection. In 2021 ieee international conference on artificial intelligence testing (aitest), (p. 83\u201384).","DOI":"10.1109\/AITEST52744.2021.00025"},{"issue":"6","key":"9744_CR72","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1109\/TSE.2024.3382365","volume":"50","author":"Y Tang","year":"2024","unstructured":"Tang, Y., Liu, Z., Zhou, Z., & Luo, X. (2024). Chatgpt vs sbst: A comparative assessment of unit test suite generation. IEEE Transactions on Software Engineering, 50(6), 1340\u20131359. https:\/\/doi.org\/10.1109\/TSE.2024.3382365","journal-title":"IEEE Transactions on Software Engineering"},{"key":"9744_CR73","unstructured":"TestLink Community (2025). TestLink: Open Source Test Management. Retrieved from https:\/\/testlink.org\/ (Accessed: 2025\u201302-08)."},{"issue":"6","key":"9744_CR74","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1109\/TSE.2025.3562025","volume":"51","author":"F Tip","year":"2025","unstructured":"Tip, F., Bell, J., & Sch\u00e4fer, M. (2025). Llmorpheus: Mutation testing using large language models. IEEE Transactions on Software Engineering, 51(6), 1645\u20131665. https:\/\/doi.org\/10.1109\/TSE.2025.3562025","journal-title":"IEEE Transactions on Software Engineering"},{"issue":"4","key":"9744_CR75","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1145\/3688007","volume":"22","author":"J Waldo","year":"2024","unstructured":"Waldo, J., & Boussard, S. (2024). Gpts and hallucination: Why do large language models hallucinate? Queue, 22(4), 19\u201333. https:\/\/doi.org\/10.1145\/3688007","journal-title":"Queue"},{"issue":"4","key":"9744_CR76","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1109\/TSE.2024.3368208","volume":"50","author":"J Wang","year":"2024","unstructured":"Wang, J., Huang, Y., Chen, C., Liu, Z., Wang, S., & Wang, Q. (2024). Software testing with large language models: Survey, landscape, and vision. IEEE Transactions on Software Engineering, 50(4), 911\u2013936. https:\/\/doi.org\/10.1109\/TSE.2024.3368208","journal-title":"IEEE Transactions on Software Engineering"},{"key":"9744_CR77","doi-asserted-by":"crossref","unstructured":"Wang, W., Yang, C., Wang, Z., Huang, Y., Chu, Z., Song, D., & Ma, L. (2025). Testeval: Benchmarking large language models for test case generation. Findings of the association for computational linguistics: Naacl 2025 (pp. 3547\u20133562).","DOI":"10.18653\/v1\/2025.findings-naacl.197"},{"issue":"2","key":"9744_CR78","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/s10515-025-00544-2","volume":"32","author":"Y Wang","year":"2025","unstructured":"Wang, Y., Zhong, W., Huang, Y., Shi, E., Yang, M., Chen, J., & Zheng, Z. (2025). Agents in software engineering: Survey, landscape, and vision. Automated Software Engineering, 32(2), 70. https:\/\/doi.org\/10.1007\/s10515-025-00544-2","journal-title":"Automated Software Engineering"},{"key":"9744_CR79","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35, 24824\u201324837.","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"9744_CR80","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s10664-023-10390-z","volume":"29","author":"D Winkler","year":"2024","unstructured":"Winkler, D., Urbanke, P., & Ramler, R. (2024). Investigating the readability of test code. Empirical Software Engineering, 29(2), 53. https:\/\/doi.org\/10.1007\/s10664-023-10390-z","journal-title":"Empirical Software Engineering"},{"key":"9744_CR81","unstructured":"Winteringham, M. (2024). Software testing with generative ai. Shelter Island, NY: Manning. (ISBN: 9781633437160)."},{"key":"9744_CR82","doi-asserted-by":"publisher","unstructured":"Xu, D., Xu, W., Tu, M., Shen, N., Chu, W., & Chang, C.-H. (2016). Automated integration testing using logical contracts. IEEE Transactions on Reliability,65(3), 1205\u20131222. https:\/\/doi.org\/10.1109\/TR.2015.2494685.","DOI":"10.1109\/TR.2015.2494685"},{"issue":"6","key":"9744_CR83","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3649506","volume":"18","author":"J Yang","year":"2024","unstructured":"Yang, J., Jin, H., Tang, R., Han, X., Feng, Q., Jiang, H., & Hu, X. (2024). Harnessing the power of llms in practice: A survey on chatgpt and beyond. ACM Trans. Knowl. Discov. Data, 18(6), 1\u201332. https:\/\/doi.org\/10.1145\/3649506","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"9744_CR84","doi-asserted-by":"crossref","unstructured":"Yeh, H.- W., Ma, S.- P., & Chen, Y. (2024). Test case migration from monolith to microservices using large language models. In 2024 ieee international conference on e-business engineering (icebe), (p. 29\u201335).","DOI":"10.1109\/ICEBE62490.2024.00014"},{"key":"9744_CR85","doi-asserted-by":"crossref","unstructured":"Yeow, J.S., Rana, M.E., & Abdul Majid, N.A. (2024). An automated model of software requirement engineering using gpt-3.5. In 2024 asu international conference in emerging technologies for sustainability and intelligent systems (icetsis), (p. 1746\u20131755).","DOI":"10.1109\/ICETSIS61505.2024.10459458"},{"key":"9744_CR86","unstructured":"ZenCart Developers (2025). ZenCart: E-commerce Platform. Retrieved from https:\/\/github.com\/zencart\/zencart (Accessed: 2025\u201302-06)."},{"key":"9744_CR87","doi-asserted-by":"publisher","unstructured":"Zhang, Q., Sun, W., Fang, C., Yu, B., Li, H., Yan, M., & Chen, Z. (2025). Exploring automated assertion generation via large language models. ACM Trans. Softw. Eng. Methodol.,34(3). Retrieved from https:\/\/doi.org\/10.1145\/3699598.","DOI":"10.1145\/3699598"},{"key":"9744_CR88","doi-asserted-by":"crossref","unstructured":"Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., & Cui, B. (2026). Retrieval-augmented generation for ai-generated content: A survey. Data Science and Engineering, 1\u201329.","DOI":"10.1007\/s41019-025-00335-5"},{"issue":"1","key":"9744_CR89","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/TPC.2016.2635720","volume":"60","author":"S Zhou","year":"2017","unstructured":"Zhou, S., Jeong, H., & Green, P. A. (2017). How consistent are the best-known readability equations in estimating the readability of design standards? IEEE Transactions on Professional Communication, 60(1), 97\u2013111.","journal-title":"IEEE Transactions on Professional Communication"}],"container-title":["Software Quality Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11219-026-09744-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11219-026-09744-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11219-026-09744-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T07:39:54Z","timestamp":1775806794000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11219-026-09744-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,21]]},"references-count":89,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["9744"],"URL":"https:\/\/doi.org\/10.1007\/s11219-026-09744-9","relation":{},"ISSN":["0963-9314","1573-1367"],"issn-type":[{"value":"0963-9314","type":"print"},{"value":"1573-1367","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,21]]},"assertion":[{"value":"3 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest\/Competing interests"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"8"}}