Practical Research on Intelligent Requirements Analysis and Test Case Generation Driven by Large Language Models

Zongshuai Wei; yajie Hu; Changmeng Chen; xuebing Chen

doi:10.63944/3v2.aia

Practical Research on Intelligent Requirements Analysis and Test Case Generation Driven by Large Language Models

Zongshuai Wei (Author)

Unit 61068 of the Chinese People’s Liberation Army, China

yajie Hu (Author)

Unit 61068 of the Chinese People’s Liberation Army, China

Changmeng Chen (Author)

Unit 61068 of the Chinese People’s Liberation Army, China

xuebing Chen (Primary Contact)

Unit 61068 of the Chinese People’s Liberation Army, China

DOI:https://doi.org/10.63944/3v2.aia

Keywords:

Large Language Model, Requirements Engineering, Requirements Analysis, Use Case Generation, Human-AI Collaboration

Published

30-01-2026

Abstract: The increasing complexity of software systems underscores that the quality and efficiency of requirements engineering, as the initial phase of the software lifecycle, directly impact project outcomes. Traditional requirements analysis heavily relies on manual effort, facing challenges such as low efficiency and difficulty in maintaining consistency. The rapid development of generative artificial intelligence, particularly large language models (LLMs), offers new tools to address these challenges. This study explores the practical application of LLMs in the software requirements analysis phase, focusing on the automated extraction and structuring of requirement elements, as well as the assisted generation of preliminary test cases. This paper proposes a “five-step” human-AI collaborative workflow incorporating large models and elaborates on its implementation steps through a retrospective case study of an intelligent warehouse management system of an intelligent warehouse management system. Practice demonstrates that this method can partially free requirements analysts from repetitive information extraction and formatting tasks, enhance the structured nature of requirements documentation, and provide valuable initial input for downstream test design. Although limitations such as model “hallucination” exist and necessitate strict manual review, this research confirms the positive potential of LLMs in standardizing and improving the efficiency of requirements engineering within software factories. Finally, the paper summarizes key experiences and challenges from the practice, providing a reference for peers seeking to introduce AI assistance in similar scenarios.

References

[1] Antonio Mastropaolo,Rick Kuhn,Jeffrey Voas. From Heuristics to Intelligence: Large Language Model-Driven Test Case Generation[J]. Computer, 2025, Vol.58(12): 130-136. DOI: https://doi.org/10.1109/MC.2025.3609478
[2] Ashley T. van CanCA1, Fabiano Dalpiaz2. Locating requirements in backlog items: Content analysis and experiments with large language models[J]. Information and Software Technology, 2025, Vol.179: 107644. DOI: https://doi.org/10.1016/j.infsof.2024.107644
[3] Marcos Galdino, Tobias Hamann, Anas Abdelrazeq,et al. Large Language Model‐Based Cognitive Assistants for Quality Management Systems in Manufacturing: A Requirement Analysis[J]. Engineering Reports, 2025, Vol.7(10): n/a.
[4] Cheng, FangminCAa, Yu, et al. Modeling and analysis method of semantic description requirements of large-scale users[J]. Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS, 2022, Vol.28(2): 601-611.
[5] Couder, Juan Ortiz, Gomez, et al. Requirements Verification Through the Analysis of Source Code by Large Language Models[C]//SoutheastCon 2024. 2024. DOI: https://doi.org/10.1109/SoutheastCon52093.2024.10500073
[6] Marcos Galdino, Tobias Hamann, Anas Abdelrazeq, et al. Large Language Model‐Based Cognitive Assistants for Quality Management Systems in Manufacturing: A Requirement Analysis[J]. Engineering Reports, 2025, Vol.7(10): n/a. DOI: https://doi.org/10.1002/eng2.70437
[7] Arthur H. M. de Oliveira, Pedro Almeida Reis, Fernando Sarracini Júnior, et al. Impact Analysis of using Natural Language Processing and Large Language Model on Automated Correction of Systems Engineering Requirements[J]. INCOSE International Symposium, 2024, Vol.34(1): 992-1007. DOI: https://doi.org/10.1002/iis2.13191
[8] Panigo, Ailen, Bankoff, et al. Tracking the Evolution of Large Language Models in Requirements Elicitation and Analysis[C]//30th Argentine Congress of Computer Science-CACIC. 2026.
[9] Ailén Panigo, Kristian Petkoff Bankoff, Ariel Pasini & Patricia Pesado. Tracking the Evolution of Large Language Models in Requirements Elicitation and Analysis[C]//Computer Science – CACIC 2024. 2025. DOI: https://doi.org/10.1007/978-3-032-00718-6_12
[10] Markus Borg. Requirements Engineering and Large Language Models: Insights From a Panel[J]. IEEE Software, 2024, Vol.41(2): 6-10. DOI: https://doi.org/10.1109/MS.2023.3339934
[11] ] M. Cohn, User Stories Applied: for Agile Software Development, Addison-Wesley Professional, 2004.
[12] Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, V. Stoyanov, RoBERTa: A robustly
[13] W.X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y. Hou, Y. Min, B. Zhang, J. Zhang, Z. Dong, et al.
[14] K. Wang, F. Zhang, M. Sabetzadeh, Automated requirements demarcation using large language models: An empirical study, in: Workshop Proceedings of REFSQ, 2024.
[15] Taohong Zhu, Lucas C. Cordeiro, Youcheng Sun. ReqInOne: A Large Language Model-Based Agent for Software Requirements Specification Generation[J]. 2025.

Practical Research on Intelligent Requirements Analysis and Test Case Generation Driven by Large Language Models

How to Cite