mlsanityData to 7 Oct 2026

Can AI Agents Generate Microservices? How Far are We?

arXiv 2603.09004 ↗First posted 9 Mar 2026cs.SEcited by 1

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

LLMs have advanced code generation, but their use for generating microservices with explicit dependencies and API contracts remains understudied. We examine whether AI agents can generate functional microservices and how different forms of contextual information influence their performance. We assess 144 generated microservices across 3 agents, 4 projects, 2 prompting strategies, and 2 scenarios. Incremental generation operates within existing systems and is evaluated with unit tests. Clean state generation starts from requirements alone and is evaluated with integration tests. We analyze functional correctness, code quality, and efficiency. Minimal prompts outperformed detailed ones in incremental generation, with 50-76% unit test pass rates. Clean state generation produced higher integration test pass rates (81-98%), indicating strong API contract adherence. Generated code showed lower complexity than human baselines. Generation times varied widely across agents, averaging 6-16 minutes per service. AI agents can produce microservices with maintainable code, yet inconsistent correctness and reliance on human oversight show that fully autonomous microservice generation is not yet achievable.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 33 of its 61 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

33 of 61 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System10 Oct
  2. 2025A Survey on Code Generation with LLM-based Agents31 Jul
  3. 2025Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories23 Jun
  4. 2025Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design26 Mar
  5. 2024HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent31 May

Other references · 28

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  3. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  4. 2024Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preferencecited by 1,151
  5. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  6. 2024A Survey on Large Language Models for Code Generationcited by 646
  7. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 468
  8. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 389
  9. 2020IntelliCode Compose: Code Generation Using Transformercited by 225
  10. 2023Better Zero-Shot Reasoning with Role-Play Promptingcited by 220
  11. 2023Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPTcited by 125
  12. 2023CodeBERTScore: Evaluating Code Generation with Pretrained Models of Codecited by 101
16 more
  1. 2023Improving Code Generation by Training with Natural Language Feedbackcited by 75
  2. 2024Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedbackcited by 45
  3. 2022Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Codecited by 39
  4. 2025LongCodeZip: Compress Long Context for Code Language Modelscited by 38
  5. 2016Microservices: yesterday, today, and tomorrowcited by 22
  6. 2025An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunitiescited by 17
  7. 2025Generative AI for Software Architecture. Applications, Challenges, and Future Directionscited by 15
  8. 2024Concerned with Data Contamination? Assessing Countermeasures in Code Language Modelcited by 14
  9. 2024The Impact of Prompt Programming on Function-Level Code Generationcited by 13
  10. 2024Artificial-Intelligence Generated Code Considered Harmful: A Road Map for Secure and High-Quality Code Generationcited by 11
  11. 2023Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Codecited by 9
  12. 2024On Large Language Models in Mission-Critical IT Governance: Are We Ready Yet?cited by 9
  13. 2025Investigating The Smells of LLM Generated Codecited by 9
  14. 2025LLMs for Generation of Architectural Components: An Exploratory Empirical Study in the Serverless Worldcited by 8
  15. 2021An Exploratory Study on the Introduction and Removal of Different Types of Technical Debtcited by 3
  16. 2024Microservices-based Software Systems Reengineering: State-of-the-Art and Future Directionscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AI Writes Code, Humans Pay the Debt. An Empirical Study on the Sustainability and Evolution of Agent-Generated Codecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025LLM Agents for Generating Microservice-based Applications: how complex is your specification?
  2. 2026To What Extent Does Agent-generated Code Require Maintenance? An Empirical Study
  3. 2025From Specification to Service: Accelerating API-First Development Using Multi-Agent Systems
  4. 2025Continuous Benchmark Generation for Evaluating Enterprise-scale LLM Agents
  5. 2025Generative AI and the Transformation of Software Development Practices
  6. 2026MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decomposition
  7. 2026Grounding AI Agents in Contracts: An Empirical Evaluation of Spec-Driven Test Generation
  8. 2026How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests