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
Automated code generation driven by Large Language Models (LLMs) has enhanced development efficiency, yet generating complex application-level software code remains challenging. Multi-agent frameworks show potential, but existing methods perform inadequately in large-scale application-level software code generation: they fail to maintain a semantically reasonable project structure and generate fragmented outputs that lack traceable requirement-to-code mappings, making them difficult to extend or scale. To address these limitations, this paper proposes KGMACG, a Knowledge-Guided Multi-Agent framework for scalable Code Generation. KGMACG orchestrates three specialized agents in a closed-loop: the Code Organization & Planning Agent (COPA) transforms software requirements specification (SRS) and architectural design document (ADD) into a modular build plan and project skeleton; the Coding Agent (CA) synthesizes repository-level code guided by a five-pillar knowledge base; and the Testing Agent (TA) continuously generates unit tests and feeds failure traces back for rectification. The loop terminates only when the project compiles and achieves \(\geq\) 95% requirement coverage, guaranteeing both syntactic correctness and functional completeness. We evaluate KGMACG on three industrial-scale case studies (E-Commerce, Campus Security, Stock Trading) against six state-of-the-art multi-agent baselines: MetaGPT, AutoGen, CAMEL, CrewAI, ChatDev and CodeAgent. With the same backbone LLMs (DeepSeek R1 and gpt-5-codex-medium), The results indicate that KGMACG advances the automation of application-level software development.
Bo Yang, Xiao Zhang, Weisong Sun et al.· ACM Transactions on Software...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
