Requirements engineering is crucial for software quality, yet requirement artefacts are often ambiguous, inconsistent, loosely traceable, and incomplete in their treatment of non-functional requirements (NFRs). These weaknesses intensify in fast-changing projects whose inputs span interviews, tickets, e-mails, policies, and regulatory text. Recent studies show growing interest in using large language models (LLMs) in requirements engineering, but the evidence base remains fragmented: most work concentrates on elicitation or validation, while ambiguity analysis, NFR handling, traceability, and requirements evolution are still largely studied as separate tasks. This paper presents a literature-grounded, AI-assisted framework that integrates these activities in a single quality-assurance lifecycle with explicit analyst oversight. The framework comprises five modules: elicitation support, specification quality analysis, functional/NFR classification, traceability and evolution management, and human validation and governance. To address reviewer concerns about the manuscript previously reading as a proposal, the revised paper adds a concrete methodological instantiation, a stronger design-science framing, and a secondary empirical synthesis from recent published studies. The synthesis shows that recent LLM-for-RE research covered 74 primary studies but remained weakly integrated in complex workflows; industrial ambiguity-detection studies already report measurable gains; traceability research continues to depend on interpretable information-retrieval baselines; and NFR research in ML-enabled systems has expanded to 31 distinct requirements grouped into six classes and 26 software-engineering challenges. The manuscript contributes an integrated framework, evidence-backed design choices, revised figures and tables, a more explicit evaluation blueprint, and an expanded reference base suitable for journal submission.

This revised manuscript responds to the major-review feedback by strengthening the literature review, clarifying the design-science methodology, adding concrete prototype choices, incorporating secondary empirical evidence from recent published studies, improving organisation and British-English style, expanding the reference section, and embedding figures and tables that make the argument easier to follow. The result is a more mature framework paper. The central claim remains that requirements quality in AI-assisted environments should be organised as a lifecycle discipline rather than as a collection of disconnected automation tools. By integrating elicitation support, specification analysis, NFR-aware classification, traceability and evolution management, and explicit human governance, the framework offers a credible basis for future empirical work and for practical experimentation in industry. The next step is straightforward: implement the blueprint and test it in one or more industrial settings with task-level and workflow-level evaluation.

Bashir, S., Ferrari, A., Abbas, M., Saadatmand, M., Enoiu, E. P., Bohlin, M., and Lindberg, P. (2025). Requirements Ambiguity Detection and Explanation with LLMs: An Industrial Study. Proceedings of ICSME 2025 Industry Track. Casamayor, A., Godoy, D., and Campo, M. (2010). Identification of non-functional requirements in textual specifications: A semi-supervised learning approach. Information and Software Technology, 52(4), 436–445. https://doi.org/10.1016/j.infsof.2009.10.010 Cleland-Huang, J., Gotel, O. C. Z., Hayes, J. H., Mäder, P., and Zisman, A. (2014). Software traceability: Trends and future directions. Proceedings of the on Future of Software Engineering, 55–69. https://doi.org/10.1145/2593882.2593891 Dalpiaz, F., Dell’Anna, D., Aydemir, F. B., and Çevikol, S. (2019). Requirements classification with interpretable machine learning and dependency parsing. 2019 IEEE 27th International Requirements Engineering Conference (RE), 142–152. https://doi.org/10.1109/RE.2019.00025 De Martino, V., and Palomba, F. (2025). Classification and challenges of non-functional requirements in ML-enabled systems: A systematic literature review. Information and Software Technology, 179, 107678. Gotel, O. C. Z., and Finkelstein, A. C. W. (1994). An analysis of the requirements traceability problem. Proceedings of the First International Conference on Requirements Engineering, 94–101. Hemmat, A. H. A., Sharbaf, M. S. M., Kolahdouz-Rahimi, S. K., Lano, K., and Tehrani, S. Y. (2025). Research directions for using LLM in software requirement engineering: a systematic review. Frontiers in Computer Science, 7, 1519437. https://doi.org/10.3389/fcomp.2025.1519437 ISO/IEC/IEEE. (2018). ISO/IEC/IEEE 29148:2018 Systems and software engineering — Life cycle processes — Requirements engineering. International Organization for Standardization / IEEE. ISO/IEC. (2023). ISO/IEC 25010 Systems and software engineering — Systems and software Quality Requirements and Evaluation (SQuaRE) — Product quality model. International Organization for Standardization. Jia, H., Morris, R., Ye, H., Sarro, F., and Mechtaev, S. (2025). Automated Repair of Ambiguous Natural Language Requirements. arXiv:2505.07270. NIST. (2023). Artificial Intelligence Risk Management Framework (AI RMF 1.0). National Institute of Standards and Technology. NIST AI 100-1. Peffers, K., Tuunanen, T., Rothenberger, M. A., and Chatterjee, S. (2007). A design science research methodology for information systems research. Journal of Management Information Systems, 24(3), 45–77. https://doi.org/10.2753/MIS0742-1222240302 Petersen, K., Vakkalanka, S., and Kuzniarz, L. (2015). Guidelines for conducting systematic mapping studies in software engineering: An update. Information and Software Technology, 64, 1–18. Porter, D., DeFranco, J. F., and Laplante, P. A. (2025). Requirements Specification Automated Quality Analysis: Past, Present, and Future. Computer, 58(1), 101–104. https://doi.org/10.1109/MC.2024.3480629 Rejithkumar, G., and Anish, P. R. (2025). NICE: Non-Functional Requirements Identification, Classification, and Explanation Using Small Language Models. Proceedings of the 2025 IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). Villamizar, H., Escovedo, T., and Kalinowski, M. (2021). Requirements Engineering for Machine Learning: A Systematic Mapping Study. 2021 47th Euromicro Conference on Software Engineering and Advanced Applications (SEAA). https://doi.org/10.1109/SEAA53835.2021.00013 Wan, H., He, X., Deng, Y., and Wang, B. (2025). A systematic mapping study of information retrieval-based requirements traceability methods. Information Processing & Management, 62(6), 104287. Zadenoori, M. A., Dąbrowski, J., Alhoshan, W., Zhao, L., and Ferrari, A. (2025). Large Language Models (LLMs) for Requirements Engineering (RE): A Systematic Literature Review. arXiv:2509.11446.