Search Results

Documents authored by Taibi, Davide

Document
Emerging Results, Vision & Reflection Track Paper
DOI: 10.4230/LIPIcs.ESEM.2026.62
Can Agents Reconstruct Microservice Architecture?

Authors: Venla Liljas, Matteo Esposito, Valentina Lenarduzzi, and Davide Taibi

Published in: LIPIcs, Volume 394, 20th International Symposium on Empirical Software Engineering and Measurement (ESEM 2026)

Abstract
Microservice architectures are increasingly becoming the standard design for cloud-native applications, yet their complex dependency structures make architectural understanding a challenge. Our research explores how Large Language Models (LLMs) can be leveraged to automatically reconstruct microservice architectures directly from source code, a task that requires both high-level architectural reasoning and fine-grained code understanding. We introduce a Minimum Viable Agent (MVA) as a single-agent that combines tool-assisted repository exploration with role-guided prompting to infer the services, inter-service connections, and exposed endpoints in Java microservice systems. We evaluate two state-of-the-art LLMs, GPT-4o and Llama4-16:17B, on 17 open-source microservice applications with 20 independent runs per system. GPT-4o achieves a mean F1 score of 0.604, outperforming Llama4 (F1 = 0.254). Both models show higher precision than recall, suggesting a tendency to under-represent architectural relationships rather than hallucinate them. Results also reveal substantial variation across applications and architectural element types. Analysis by architectural element indicates that service-to-service connections are the most challenging to recover for both models, while large performance differences emerge from endpoint reconstruction. Overall, our findings suggest that LLMs show promise for automated architecture recovery, but current capabilities remain insufficient for fully reliable reverse engineering. We discuss implications for integrating LLMs into architecture analysis workflows and outline directions for future research.
Cite as

Venla Liljas, Matteo Esposito, Valentina Lenarduzzi, and Davide Taibi. Can Agents Reconstruct Microservice Architecture?. In 20th International Symposium on Empirical Software Engineering and Measurement (ESEM 2026). Leibniz International Proceedings in Informatics (LIPIcs), Volume 394, pp. 62:1-62:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{liljas_et_al:LIPIcs.ESEM.2026.62,
  author =	{Liljas, Venla and Esposito, Matteo and Lenarduzzi, Valentina and Taibi, Davide},
  title =	{{Can Agents Reconstruct Microservice Architecture?}},
  booktitle =	{20th International Symposium on Empirical Software Engineering and Measurement (ESEM 2026)},
  pages =	{62:1--62:13},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-450-5},
  ISSN =	{1868-8969},
  year =	{2026},
  volume =	{394},
  editor =	{Feldt, Robert and Paasivaara, Maria and Mendez, Daniel and Wagner, Stefan and Bar\'{o}n, Marvin Mu\~{n}oz},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ESEM.2026.62},
  URN =		{urn:nbn:de:0030-drops-280302},
  doi =		{10.4230/LIPIcs.ESEM.2026.62},
  annote =	{Keywords: Large Language Models, Microservice Architecture, Software Architecture Reconstruction, Agentic AI}
}
Document
DOI: 10.4230/OASIcs.Microservices.2020-2022.2
Microservice-Aware Static Analysis: Opportunities, Gaps, and Advancements

Authors: Tomas Cerny and Davide Taibi

Published in: OASIcs, Volume 111, Joint Post-proceedings of the Third and Fourth International Conference on Microservices (Microservices 2020/2022)

Abstract
Microservice architecture is the mainstream to fuel cloud-native systems with small service sets developed and deployed independently. The independent nature of this modular architecture also leads to challenges and gaps practitioners did not face in system monoliths. One of the major challenges with decentralization and its independent microservices that are managed by separate teams is that the evolving system architecture easily deviates far from the original plans, and it becomes difficult to maintain. Literature often refers to this process as system architecture degradation. Especially in the context of microservices, available tools are limited. This article challenges the audience on how static analysis could contribute to microservice system development and management, particularly managing architectural degradation. It elaborates on challenges and needed changes in the traditional code analysis to better fit these systems. Consequently, it discusses implications for practitioners once robust static analysis tools become available.
Cite as

Tomas Cerny and Davide Taibi. Microservice-Aware Static Analysis: Opportunities, Gaps, and Advancements. In Joint Post-proceedings of the Third and Fourth International Conference on Microservices (Microservices 2020/2022). Open Access Series in Informatics (OASIcs), Volume 111, pp. 2:1-2:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{cerny_et_al:OASIcs.Microservices.2020-2022.2,
  author =	{Cerny, Tomas and Taibi, Davide},
  title =	{{Microservice-Aware Static Analysis: Opportunities, Gaps, and Advancements}},
  booktitle =	{Joint Post-proceedings of the Third and Fourth International Conference on Microservices (Microservices 2020/2022)},
  pages =	{2:1--2:14},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-306-5},
  ISSN =	{2190-6807},
  year =	{2023},
  volume =	{111},
  editor =	{Dorai, Gokila and Gabbrielli, Maurizio and Manzonetto, Giulio and Osmani, Aomar and Prandini, Marco and Zavattaro, Gianluigi and Zimmermann, Olaf},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.Microservices.2020-2022.2},
  URN =		{urn:nbn:de:0030-drops-194647},
  doi =		{10.4230/OASIcs.Microservices.2020-2022.2},
  annote =	{Keywords: Microservice Architecture, Static Analysis, Reasoning, Decentralization}
}

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact