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

TL;DR

This paper introduces KGACG, a multi-agent framework that leverages knowledge guidance and a collaborative loop to improve the automation and organization of application-level software code generation from specifications.

Contribution

It proposes a novel multi-agent framework with a feedback mechanism that enhances code organization and quality in large-scale application development.

Findings

Successful implementation in a Java Tank Battle game case study

Improved code organization and maintainability

Effective collaboration among agents in code generation process

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 & 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.