requirements translation

Existing research lacks a systematic integration of how domain knowledge is effectively elicited, formalized, and sustainably maintained in Requirements Engineering (RE). To address this gap, we employed a hybrid retrieval and iterative snowballing approach to systematically analyze 75 primary studies, thereby establishing— for the first time—the foundational Knowledge-Driven Requirements Engineering (KDRE) framework. Our analysis reveals domain knowledge’s pivotal role in understanding system context, reconciling stakeholder concerns, and resolving requirement ambiguity. We further map its application patterns and challenges across mainstream requirement types (e.g., functional, non-functional), critical quality attributes (e.g., scalability, security), and knowledge management practices (e.g., traceability, evolution). The study identifies three key research directions: scalable knowledge representation, automated knowledge integration, and sustainable tool-chain embedding. This work provides RE researchers and practitioners with a rigorous methodological foundation and a clear roadmap for future investigation and practice.

This work addresses the inefficiency and high cost of compliance testing in highly regulated domains, where current practices rely on manual translation of regulations into test cases by experts. While large language models (LLMs) offer automation potential, they often suffer from hallucination, and existing hybrid approaches still require significant human modeling effort. To overcome these limitations, the authors propose RAFT, a novel framework that explicitly extracts implicit regulatory knowledge from multiple LLMs and leverages an adaptive purification-aggregation strategy with dynamic prompt injection to automatically generate domain-specific meta-models, formalized requirements, and testability constraints—enabling fully automated, human-intervention-free compliance test generation. Experiments in financial, automotive, and power sectors demonstrate that RAFT achieves expert-level performance, significantly outperforming state-of-the-art methods while drastically reducing test case generation and review time.

This work proposes a structured prompting framework leveraging large language models (LLMs) to reduce the human effort and complexity inherent in Domain-Driven Design (DDD) implementation. The approach decomposes the DDD process into five sequential steps: event storming simulation, bounded context identification, aggregate design, glossary generation, and technical architecture mapping. It represents the first systematic application of prompt engineering across the entire DDD workflow, positioning the LLM as an expert collaborator rather than a replacement for human designers. Experimental results demonstrate that the first three steps effectively produce high-quality design artifacts—such as domain glossaries and context maps—whereas the latter two steps suffer from error propagation, thereby underscoring the necessity of human-in-the-loop collaboration for critical design decisions.

This work addresses the widespread absence of systematic quality assurance mechanisms in enterprise deployments of generative AI systems, which hinders the establishment of organizational trust. To bridge this gap, the paper proposes a novel four-stage quality assurance framework centered on domain experts, encompassing structured specification definition, system construction, expert-driven testing and validation, and continuous production monitoring. For the first time, this approach deeply integrates domain expertise throughout the entire generative AI engineering lifecycle. By doing so, it effectively reconciles the capabilities of generative AI with organizational trust requirements, ensuring authoritative expert oversight and high-quality outputs across diverse application scenarios, thereby significantly enhancing enterprises’ capacity for trustworthy deployment of generative AI systems.

This work addresses the frequent failure of large language model (LLM) agents in enterprise tasks due to a lack of domain-specific “tribal knowledge”—such as specialized terminology, workflows, and policies—and the inefficiency of conventional knowledge engineering approaches. Inspired by test-driven development, the authors propose a problem-first, failure-driven methodology that inverts traditional knowledge acquisition: when an agent fails on a real-world task, it actively requests the minimal set of knowledge required to resolve the specific issue. By integrating an entity metamodel with a semi-automated curation mechanism, this approach enables precise and efficient knowledge capture. Evaluated in a retail order fulfillment scenario, the method constructed a reusable knowledge base comprising 46 entities in just nine problem-resolution cycles, demonstrating both effectiveness and scalability.

This work addresses the semantic gap between tactical Domain-Driven Design (DDD) patterns and general-purpose modeling languages, which often leads to persistent misalignment between design intent and code implementation. To bridge this gap, the authors propose a DDD-native metamodel that treats tactical DDD constructs as first-class modeling primitives and embeds expert architectural knowledge as executable constraints. Integrated with a real-time constraint validation engine and a bidirectional round-trip engineering mechanism, the approach ensures continuous consistency between models and code. By doing so, it substantially lowers the barrier to adopting tactical DDD, transforming it from an expert-dependent, elite practice into a tool-supported, widely reusable engineering methodology.

In safety-critical and regulated domains, existing requirements engineering practices struggle to systematically support explainability requirements, facing challenges such as conceptual ambiguity, insufficient expressiveness in specification, and fragmented validation approaches. This study employs a multi-stage qualitative methodology—including think-aloud protocols, facilitated group discussions, and cross-phase analysis of requirements engineering activities—to investigate how Daimler Truck engineers address explainability requirements in real-world projects. For the first time, it identifies explainability challenges that span the entire requirements lifecycle—from elicitation and specification to verification—thereby laying an empirical foundation for an explainable AI (XAI)-oriented requirements engineering framework and addressing the notable gap in practice-driven approaches within this field.

SBST suffers from insufficient domain knowledge integration, leading to semantically invalid test cases and low defect detection rates. To address this, we propose an empirical anomaly-driven reflective paradigm that challenges conventional knowledge-fusion assumptions, introducing two novel concepts: *domain-intent modeling* and *interpretable knowledge embedding*. Methodologically, we integrate evolutionary algorithms, constraint solving, and domain ontologies to design a knowledge-guided fitness function reconstruction mechanism and a test input space pruning strategy. Evaluated across multiple industrial-grade embedded systems, our approach achieves a 37% improvement in defect detection rate, a 2.1× increase in accuracy for identifying critical logic errors, and a significant reduction in redundant test executions. This work establishes a theoretical framework and practical methodology for transitioning SBST from algorithm-centric to knowledge-enhanced testing.

This work addresses the limited reliability of structured security artifacts—such as KQL queries and MITRE ATT&CK mappings—generated by large language models, which often fall short of production-grade requirements. To bridge this gap, the authors propose a lightweight verification framework that shifts the focus of quality assurance from generation to validation. The core innovations include a hybrid testing strategy integrating test-driven generation, deterministic program verification, and semantic evaluation by large language models, alongside an interpretable judging mechanism distilled from expert decision distributions. Deployed in Microsoft Sentinel’s production environment, the framework significantly enhances the reliability of three critical types of security artifacts, establishing professional-grade and scalable validation standards.

This work addresses the challenge that non-experts often produce low-quality visualizations in specialized domains due to insufficient domain knowledge, thereby consuming substantial expert time and creating organizational bottlenecks. To overcome this, the paper introduces the first systematic framework that structures experts’ tacit knowledge into explicit rules and design principles, integrating a request classifier, retrieval-augmented generation (RAG), and a multi-agent architecture to enhance large language models’ (LLMs) autonomous, reactive, proactive, and social capabilities. Evaluated across five engineering scenarios, the approach achieves a 206% improvement in output quality, with all generated visualizations rated at expert level; furthermore, the synthesized code exhibits higher quality and lower variance compared to baseline methods.