KGMACG: Knowledge-Guided Multi-Agent Orchestration for Scalable Application-Level Code Generation
TL;DR
KGMACG is evaluated on three industrial-scale case studies against six state-of-the-art multi-agent baselines: MetaGPT, AutoGen, CAMEL, CrewAI, ChatDev and CodeAgent and indicates that KGMACG advances the automation of application-level software development.
Abstract
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.