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

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Danyllo Albuquerque, José Renan, Guillermo Rodríguez, Guillermo Rodríguez, Emanuel Dantas, Ademar França, Mirko Perkusich, Kyller Gorgônio, Angelo Perkusich
• Venue: arXiv: cs.SE
• Published: 2026-07-30
• Collected: 2026-07-31
• URL: http://arxiv.org/abs/2607.28307v1
• PDF: https://arxiv.org/pdf/2607.28307v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers evaluated the ability of a Large Language Model (OpenAI o3) to generate microservice architectures based on textual requirements. The study found that the LLM was more effective when given examples (few-shot prompting), identifying services with higher agreement and producing architectures perceived as more modular, coherent, and plausible than with zero-shot prompting. However, the results are limited to two small systems and may not be universally applicable.

What the Document Says

• The study investigates whether an LLM can generate microservice architectures solely from textual requirements.
• OpenAI o3 identifies services with higher agreement under few-shot prompting compared to zero-shot prompting.
• Communication recovery is more challenging and improved under few-shot prompting.
• Expert evaluation corroborates these results, with few-shot architectures perceived as more modular, coherent, and plausible than zero-shot outputs.

Key Concepts Mentioned

• Microservice architectures
• Large Language Models (LLMs)
• Textual requirements
• Service identification
• Communication recovery
• Expert evaluation

Claims Made by the Document

• OpenAI o3 can generate microservice architectures from textual requirements.
• Few-shot prompting improves service identification and communication recovery compared to zero-shot prompting.

Evidence Used

• Results show higher agreement for few-shot prompting in service identification.
• Improved F1 scores for few-shot prompting in communication recovery.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.