KGMACG: Knowledge-Guided Multi-Agent Orchestration for Scalable Application-Level Code Generation
ACM Transactions on Software Engineering and Methodology · 30.11.2026 · 35 (11) · 1-29
DOI: 10.1145/3842390 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 04.11.2026. Verfasst von Bo Yang und 10 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Key R&D Program of China.
Abstract (Originalsprache)
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 article proposes KGMACG , a K nowledge- G uided M ulti- A gent framework for scalable C ode G eneration. KGMACG orchestrates three specialized agents in a closed-loop: the Code Organization and 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.
Förderung
- National Key R&D Program of China
Zitieren
APA
Yang, B., Zhang, X., Sun, W., Ma, G., Liu, H., Yang, X., Xiong, Q., Zhang, Y., Li, T., Liu, Y., & Jin, Z. (2026). KGMACG: Knowledge-Guided Multi-Agent Orchestration for Scalable Application-Level Code Generation. ACM Transactions on Software Engineering and Methodology, 35(11), 1-29. https://doi.org/10.1145/3842390
Vancouver
Yang B, Zhang X, Sun W, Ma G, Liu H, Yang X, et al. KGMACG: Knowledge-Guided Multi-Agent Orchestration for Scalable Application-Level Code Generation. ACM Transactions on Software Engineering and Methodology. 2026;35(11):1-29. doi:10.1145/3842390
BibTeX
@article{Yang2026,
author = {Yang, Bo and Zhang, Xiao and Sun, Weisong and Ma, Guohao and Liu, Han and Yang, Xiaowei and Xiong, Qian and Zhang, Yiran and Li, Tianlin and Liu, Yang and Jin, Zhi},
title = {KGMACG: Knowledge-Guided Multi-Agent Orchestration for Scalable Application-Level Code Generation},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2026},
volume = {35},
number = {11},
pages = {1--29},
doi = {10.1145/3842390}
}
EUVIMED