Requirements engineering is a critical yet labor-intensive phase in software development, particularly for complex systems where stakeholder needs are diverse, evolving, and often ambiguous. Traditional approaches struggle with scalability, consistency, and completeness when dealing with large-scale requirements. This paper proposes MA-HAI-RGF, a Multi-Agent Human-AI Collaborative Requirements Generation Framework designed to address these challenges through intelligent automation and effective human-AI collaboration. The framework employs a multi-agent architecture with specialized roles including elicitor, analyzer, validator, and prioritizer agents that work collaboratively with human stakeholders. We introduce interaction protocols for human-in-the-loop engagement, automated consistency checking mechanisms, and conflict resolution strategies. To make the empirical basis explicit, we evaluate the framework through a DeepSeek-V4-Flash simulation benchmark over three complex-system domains. Compared with a single-stage AI baseline, MA-HAI-RGF reduces the mean Validator-detected conflict rate from 12.5% to 8.3% and the mean ambiguity count from 5.0 to 0.7. The framework therefore improves the quality and reviewability of generated requirements while maintaining explicit stakeholder approval gates.
Ming-Hao Li, Chong-Shuang Hu, Han Liu et al.· 2026 12th International Conf...· 0 citations
Cross-phase collaborative management in complex product systems (CoPS) development is inherently challenged by heterogeneous organizational coupling and stochastic disturbances. Although digital twin (DT) and model-based systems engineering (MBSE) technologies provide foundations for physical–virtual synchronization and model traceability, existing approaches remain fragmented in three respects: insufficient requirements-traceable architectural integration, limited cross-phase semantic interoperability and runtime evolution, and weak operational links between semantic reasoning and adaptive decision models. To address these gaps, this paper proposes an MBSE-driven digital twin framework with semantic enhancement. First, a four-layer architecture is derived using the MagicGrid methodology, encompassing physical–virtual mapping, semantic reasoning, decision support, and service interaction. Second, a collaboration-oriented SysML profile is developed to standardize the representation of tasks, resources, materials, disturbances, and management constraints across engineering phases. Third, a knowledge-driven adaptive collaboration mechanism maps runtime disturbance inputs into semantic states, propagates their cross-phase impacts, supports process-topology reconfiguration, and generates decision-ready constraints for adaptive management. A case-based prototype for aero-engine turbofan blade development demonstrates the feasibility of the mapping–reasoning–decision chain and provides case-level evidence of improved cross-phase coordination under controlled disturbance scenarios. The results indicate a feasible engineering pathway from perceptive DT functions toward reasoning-enabled collaborative decision support.
Zhu Xiang, Ming-Hao Li, Tian-Yang Lei et al.· Systems· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
