From Textual Requirements to Microservice Architectures - A Comprehensive Evaluation of LLM-Based Design Synthesis

2026-07-30

AI Summary

This study addresses the challenge of automatically constructing microservice architectures from natural language requirements during early design stages, where only unstructured textual specifications are available. It presents the first systematic evaluation of large language models (LLMs) in generating end-to-end microservice architectures under zero-shot and few-shot settings. Leveraging the OpenAI o3 model with structured prompting strategies, the work employs a hybrid evaluation framework combining F1 scores and expert blind reviews. Experimental results demonstrate that few-shot prompting substantially improves the accuracy of service identification (F1=0.97) and communication relationship recovery (F1=0.82). Moreover, expert assessments indicate that the generated architectures exhibit superior modularity, reasonableness, and coherence, highlighting the critical role of exemplar-based prompting in enhancing architectural quality.

Abstract

Microservice architectures have become dominant for modernizing monolithic systems, yet identifying appropriate services remains challenging and largely manual. Existing decomposition approaches are predominantly code-centric, limiting applicability in early design stages where only textual requirements are available. Despite advances in Large Language Models (LLMs), limited empirical evidence exists on their ability to synthesize complete microservice architectures from natural-language requirements, including service definitions and inter-service interactions. This study investigates whether an LLM can bridge requirements engineering and architectural design, generating architectures solely from textual requirements and evaluating structural agreement and perceived quality of results. We conduct a mixed-method study using OpenAI o3 under zero-shot (ZS) and few-shot (FS) prompting across two systems (Bookstore, PetClinic), one execution per system/condition. Architectures are evaluated through (i) comparison with reference architectures using precision, recall, and F1-score for service identification and communication recovery, and (ii) a blinded expert assessment of correctness, completeness, modularity, and plausibility, plus open feedback synthesis. OpenAI o3 identifies services with higher agreement under FS prompting (F1 = 0.79 for ZS versus = 0.97 for FS). Communication recovery is more challenging: ZS produces dense architectures with high recall but low precision (F1 = 0.61), while FS improves agreement, reaching F1 = 0.82 and reducing unsupported dependencies. Expert evaluation corroborates these results, with FS architectures perceived as more modular, coherent, and plausible than ZS outputs. OpenAI o3 shows potential for requirements-driven synthesis when guided by exemplar prompting. Results are model- and context-specific from two small systems, not model-independent proof.

Problem

• microservice architecture
• requirements engineering
• LLM-based design synthesis
• service identification
• architectural design

Innovation

• LLM-based design synthesis
• microservice decomposition
• few-shot prompting
• requirements-driven architecture
• architectural evaluation