Autonomous Legacy Web Application Upgrades Using a Multi-Agent System

TL;DR

This paper presents a multi-agent system leveraging Large Language Models to autonomously upgrade legacy web applications, demonstrating improved accuracy and context maintenance over standalone models in code updating tasks.

Contribution

It introduces a novel LLM-based multi-agent framework for automated legacy web application upgrades, addressing complexity and cost issues of manual updates.

Findings

System maintains context across tasks and agents.

Improves solution quality over base LLM models.

High precision in updating small outdated files.

Abstract

The use of Large Language Models (LLMs) for autonomous code generation is gaining attention in emerging technologies. As LLM capabilities expand, they offer new possibilities such as code refactoring, security enhancements, and legacy application upgrades. Many outdated web applications pose security and reliability challenges, yet companies continue using them due to the complexity and cost of upgrades. To address this, we propose an LLM-based multi-agent system that autonomously upgrades legacy web applications to the latest versions. The system distributes tasks across multiple phases, updating all relevant files. To evaluate its effectiveness, we employed Zero-Shot Learning (ZSL) and One-Shot Learning (OSL) prompts, applying identical instructions in both cases. The evaluation involved updating view files and measuring the number and types of errors in the output. For complex tasks, we counted the successfully met requirements. The experiments compared the proposed system with standalone LLM execution, repeated multiple times to account for stochastic behavior. Results indicate that our system maintains context across tasks and agents, improving solution quality over the base model in some cases. This study provides a foundation for future model implementations in legacy code updates. Additionally, findings highlight LLMs' ability to update small outdated files with high precision, even with basic prompts. The source code is publicly available on GitHub: https://github.com/alasalm1/Multi-agent-pipeline.