From Specification to Service: Accelerating API-First Development Using Multi-Agent Systems
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
This paper presents a system that uses Large Language Models (LLMs)-based agents to automate the API-first development of RESTful microservices. This system helps to create an OpenAPI specification, generate server code from it, and refine the code through a feedback loop that analyzes execution logs and error messages. The integration of log analysis enables the LLM to detect and address issues efficiently, reducing the number of iterations required to produce functional and robust services. This study's main goal is to advance API-first development automation for RESTful web services and test the capability of LLM-based multi-agent systems in supporting the API-first development approach. To test the proposed system's potential, we utilized the PRAB benchmark. The results indicate that if we keep the OpenAPI specification small and focused, LLMs are capable of generating complete functional code with business logic that aligns to the specification. The code for the system is publicly available at https://github.com/sirbh/code-gen
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 18 of its 43 references that are in the map. First posted on arXiv 22 Oct 2025.
Builds on
18 of 43 references.
References · 18
- 2017Deep reinforcement learning from human preferencescited by 3,912
- 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
- 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
- 2023A Survey on Evaluation of Large Language Modelscited by 1,242
- 2024A Survey on Large Language Models for Code Generationcited by 658
- 2023A Comprehensive Overview of Large Language Modelscited by 648
- 2023Large Language Models for Software Engineering: Survey and Open Problemscited by 181
- 2023An LLM Compiler for Parallel Function Callingcited by 179
- 2024AI-powered Code Review with LLMs: Early Resultscited by 22
- 2024Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysiscited by 20
- 2024Asynchronous LLM Function Callingcited by 18
- 2023Enhancing Large Language Models for Secure Code Generation: A Dataset-driven Study on Vulnerability Mitigationcited by 15
6 more
- 2023Practices and Challenges of Using GitHub Copilot: An Empirical Studycited by 14
- 2023Microservice API Evolution in Practice: A Study on Strategies and Challengescited by 7
- 2025LLM-Generated Microservice Implementations from RESTful API Definitionscited by 5
- 2024SpeCrawler: Generating OpenAPI Specifications from API Documentation Using Large Language Modelscited by 2
- 2024TimeLess: A Vision for the Next Generation of Software Developmentcited by 2
- 2024Custom Developer GPT for Ethical AI Solutionscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025LLM Agents for Generating Microservice-based Applications: how complex is your specification?
- 2025A Framework for Testing and Adapting REST APIs as LLM Tools
- 2026Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis
- 2025From REST to MCP: An Empirical Study of API Wrapping and Automated Server Generation for LLM Agents
- 2026OOPS: Automated generation of REST API specification via LLMs ↗
- 2026Making OpenAPI Documentation Agent-Ready: Detecting Documentation and REST Smells with a Multi-Agent LLM System
- 2026DADL: A Declarative Description Language for Enterprise Tool Libraries in LLM Agent Systems
- 2025A Declarative Language for Building And Orchestrating LLM-Powered Agent Workflows