MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decomposition

2026-06-28

AI Summary

This work addresses the challenge of migrating legacy monolithic applications to microservice architectures, where existing approaches often fail to balance design principles due to insufficient semantic understanding and contextual awareness. To overcome these limitations, the authors propose the first automated decomposition framework that integrates multi-agent collaboration, multi-granularity context enhancement, and explicit constraints derived from microservice design principles. The framework employs five specialized agents that collaboratively perform service decomposition, guided by a context-aware mechanism and principle-driven analytical tools to inform decision-making. Experimental evaluation on ten real-world Java web applications demonstrates that the proposed method achieves an average decomposition accuracy of 89.2%, representing a 24.6% improvement over the current state-of-the-art, thereby significantly enhancing both the accuracy and practicality of microservice extraction.

Abstract

The adoption of Microservice Architecture (MSA) has revolutionized software engineering by enhancing scalability, agility, and maintainability over traditional monolithic applications. As more developers transition their legacy systems to microservice-based architectures, effective microservice decomposition-partitioning monolithic applications into highly cohesive services-becomes vital. However, this decomposition task presents significant challenges. Manual approaches are time-consuming and labor-intensive. Existing automated methods often fail to capture the necessary semantic insights from complex applications, while naive applications of Large Language Models tend to overlook crucial contextual information and design principles, leading to suboptimal results. To address these challenges, we propose MicroAgent, a Context-Augmented Multi-Agent Framework for Microservice Decomposition. Our framework divides the decomposition process into five distinct subtasks and assigns each to a specialized agent. To enhance the effectiveness of each agent, we provide tailored, multi-granularity context that keeps its analysis focused and mitigates information overload. Furthermore, to ensure the decomposition adheres to established design principles, we integrate analytical tools that guide the agents' decision-making. Experimental evaluations on 10 Java Web applications demonstrate that MicroAgent achieves an average decomposition accuracy of 89.2%, outperforming the state-of-the-art method by 24.6%. We also conduct a case study to highlight the practical benefits of our design.

Problem

• Microservice Decomposition
• Context-Awareness
• Large Language Models
• Software Architecture
• Automated Refactoring

Innovation

• Microservice Decomposition
• Multi-Agent Framework
• Context-Augmented LLM
• Software Architecture
• Automated Refactoring