{"ID":2851472,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.19868","arxiv_id":"2510.19868","title":"Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation","abstract":"Automated code generation driven by Large Lan- guage 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, failing to ensure reasonable orga- nizational structures of project code and making it difficult to maintain the code generation process. To address this, this paper envisions a Knowledge-Guided Application-Level Code Generation framework named KGACG, which aims to trans- form software requirements specification and architectural design document into executable code through a collaborative closed- loop of the Code Organization \u0026 Planning Agent (COPA), Coding Agent (CA), and Testing Agent (TA), combined with a feedback mechanism. We demonstrate the collaborative process of the agents in KGACG in a Java Tank Battle game case study while facing challenges. KGACG is dedicated to advancing the automation of application-level software development.","short_abstract":"Automated code generation driven by Large Lan- guage 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,...","url_abs":"https://arxiv.org/abs/2510.19868","url_pdf":"https://arxiv.org/pdf/2510.19868v1","authors":"[\"Qian Xiong\",\"Bo Yang\",\"Weisong Sun\",\"Yiran Zhang\",\"Tianlin Li\",\"Yang Liu\",\"Zhi Jin\"]","published":"2025-10-22T03:10:58Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[\"Large Language Model\",\"Generative Adversarial Network\"]","has_code":false}