Software testing is critical for verifying that systems meet specified requirements, yet remains among the most time-consuming and expensive activities in development. Requirements-based test generation allows test cases to be derived early from requirements artifacts, but generating them directly from natural language is challenging due to inherent ambiguity and imprecision. Recent advances in AI, natural language processing (NLP), and large language models (LLMs) have made automating this pipeline increasingly feasible, while introducing new risks including hallucination, reduced traceability, and inconsistent evaluation. This survey addresses four research questions: what AI and NLP techniques have been proposed for generating test cases from natural language requirements; what tools and frameworks support these approaches; how generated test cases are evaluated; and what research gaps remain. Following Kitchenham and Charters' systematic review guidelines, we searched major scholarly databases spanning 2000-2025 and, after applying strict inclusion criteria, identified 21 primary studies. The literature is organized into three evolutionary eras, revealing that no existing approach simultaneously satisfies six key quality dimensions: automation, ambiguity handling, domain applicability, traceability, evaluation thoroughness, and hallucination control. The survey makes three main contributions: a three-era evolutionary synthesis of AI-based test generation; a six-criteria gap analysis showing no current approach fully addresses all quality dimensions; and four actionable research guidelines targeting hallucination, traceability, complexity sensitivity, and compliance.
Transparency as Architecture: Structural Compliance Gaps in EU AI Act Article 50 II
Technichal University Berlin XpaliNLP Group(柏林工业大学 XpaliNLP 组);Research Center for Artificial Intelligence (DFKI)(人工智能研究中心(DFKI));Center for European Research on Trusted AI (CERTAIN)(欧洲可信人工智能研究中心(CERTAIN))
Requirements Practices and Gaps When Engineering Human-Centered Artificial Intelligence Systems
工程人工智能(AI)软件是一个相对较新的领域,有许多挑战,未知数和有限的证明最佳实践。谷歌、微软和苹果等大公司最近提供了一套指导方针,以帮助工程团队构建以人为本的人工智能系统。[目的]实践者目前所采用的开发这样的系统,特别是在需求工程(RE),很少研究和报告的日期。[方法]本文介绍了一项调查的结果,旨在了解当前的RE for AI(RE4AI)行业实践,并确定应遵循哪些关键的以人为本的AI指南。我们的调查是基于映射现有的行业准则,最佳实践和文献中的努力。[结果] 29名专业人士认为,RE中所有以人为本的方面都应该得到重视。此外,我们发现大多数参与者使用UML或Microsoft Office来呈现需求。[结论]我们发现,目前使用的大多数工具都不适合管理基于AI的软件,使用UML和Office可能会对AI捕获的需求质量造成问题。此外,从指南中映射的所有以人为本的实践都应该包括在RE中。
How Mature is Requirements Engineering for AI-based Systems? A Systematic Mapping Study on Practices, Challenges, and Future Research Directions
University of Stuttgart(斯图加特大学);University of Kotli Azad Jammu and Kashmir(阿扎德查谟和克什米尔科特利大学);Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);Technical University of Munich(慕尼黑工业大学)
Awareness requirement and performance management for adaptive systems: a survey
University of Kurdistan Hewler(库尔德斯坦赫勒大学);Charles Sturt University(查尔斯特大学);Western Sydney University(西悉尼大学);Kent Institute Australia(澳大利亚肯特学院);University College of Goizha(戈伊扎大学学院);Ramco Institute of Technology(拉姆科理工学院);Guru Nanak Dev University(古鲁那纳克德夫大学);King Fahd University of Petroleum & Minerals(法赫德国王石油与矿产大学);Charmo University(查尔莫大学);Sulaimani Polytechnic University(苏莱曼尼理工大学)
Requirements-Based Test Generation: A Comprehensive Survey
Macau University of Science and Technology(澳门科技大学);Zhejiang Polytechnic University of Mechanical and Electrical Engineering(浙江机电职业技术学院);Macau University of Science and Technology Zhuhai MUST Science and Technology Research Institute(澳门科技大学珠海MUST科技研究院);University of Cincinnati(辛辛那提大学);University of Nottingham Ningbo China(诺丁汉大学宁波校区)