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

arXiv: https://arxiv.org/abs/2607.28307 · HTML: https://mlsanity.com/paper/2607.28307/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 44 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 10 of 10)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Towards an Understanding of Large Language Models in Software Engineering Tasks](https://mlsanity.com/paper/2308.11396/) (2023)
- [A Survey on Large Language Models for Software Engineering](https://mlsanity.com/paper/2312.15223/) (2023)
- [Microservices: yesterday, today, and tomorrow](https://mlsanity.com/paper/1606.04036/) (2016)
- [Can LLMs Generate Architectural Design Decisions? -An Exploratory Empirical study](https://mlsanity.com/paper/2403.01709/) (2024)
- [From Monolith to Microservices: A Classification of Refactoring Approaches](https://mlsanity.com/paper/1807.10059/) (2018)
- [A curated Dataset of Microservices-Based Systems](https://mlsanity.com/paper/1909.03249/) (2019)
- [Insights on Microservice Architecture Through the Eyes of Industry Practitioners](https://mlsanity.com/paper/2408.10434/) (2024)
- [A Systematic Literature Review of Machine Learning Approaches for Migrating Monolithic Systems to Microservices](https://mlsanity.com/paper/2508.15941/) (2025)

## Abstract (arXiv)

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.