# Can AI Agents Generate Microservices? How Far are We?

arXiv: https://arxiv.org/abs/2603.09004 · HTML: https://mlsanity.com/paper/2603.09004/

## Key facts

- Cited by 1 papers in the map (data through 14 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.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 33)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [Better Zero-Shot Reasoning with Role-Play Prompting](https://mlsanity.com/paper/2308.07702/) (2023)
- [Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPT](https://mlsanity.com/paper/2304.00385/) (2023)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code](https://mlsanity.com/paper/2302.05527/) (2023)
- [Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories](https://mlsanity.com/paper/2506.18824/) (2025)
- [Improving Code Generation by Training with Natural Language Feedback](https://mlsanity.com/paper/2303.16749/) (2023)
- [Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback](https://mlsanity.com/paper/2403.16792/) (2024)
- [Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Code](https://mlsanity.com/paper/2206.01335/) (2022)
- [LongCodeZip: Compress Long Context for Code Language Models](https://mlsanity.com/paper/2510.00446/) (2025)
- [HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent](https://mlsanity.com/paper/2406.00215/) (2024)
- [Microservices: yesterday, today, and tomorrow](https://mlsanity.com/paper/1606.04036/) (2016)
- [An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities](https://mlsanity.com/paper/2501.13742/) (2025)
- [Generative AI for Software Architecture. Applications, Challenges, and Future Directions](https://mlsanity.com/paper/2503.13310/) (2025)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Concerned with Data Contamination? Assessing Countermeasures in Code Language Model](https://mlsanity.com/paper/2403.16898/) (2024)
- [The Impact of Prompt Programming on Function-Level Code Generation](https://mlsanity.com/paper/2412.20545/) (2024)
- [Artificial-Intelligence Generated Code Considered Harmful: A Road Map for Secure and High-Quality Code Generation](https://mlsanity.com/paper/2409.19182/) (2024)
- [Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code](https://mlsanity.com/paper/2310.10508/) (2023)
- [On Large Language Models in Mission-Critical IT Governance: Are We Ready Yet?](https://mlsanity.com/paper/2412.11698/) (2024)
- [Investigating The Smells of LLM Generated Code](https://mlsanity.com/paper/2510.03029/) (2025)
- [LLMs for Generation of Architectural Components: An Exploratory Empirical Study in the Serverless World](https://mlsanity.com/paper/2502.02539/) (2025)

## Built on by (most cited first, 1 of 1)

- [AI Writes Code, Humans Pay the Debt. An Empirical Study on the Sustainability and Evolution of Agent-Generated Code](https://mlsanity.com/paper/2609.04208/) (2026)

## 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.