Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xiong, Qian, Yang, Bo, Sun, Weisong, Zhang, Yiran, Li, Tianlin, Liu, Yang, Jin, Zhi
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917035491983360
author Xiong, Qian
Yang, Bo
Sun, Weisong
Zhang, Yiran
Li, Tianlin
Liu, Yang
Jin, Zhi
author_facet Xiong, Qian
Yang, Bo
Sun, Weisong
Zhang, Yiran
Li, Tianlin
Liu, Yang
Jin, Zhi
contents 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 & 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19868
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation
Xiong, Qian
Yang, Bo
Sun, Weisong
Zhang, Yiran
Li, Tianlin
Liu, Yang
Jin, Zhi
Software Engineering
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 & 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.
title Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation
topic Software Engineering
url https://arxiv.org/abs/2510.19868