# LLM as a code generator in Agile Model Driven Development

arXiv: https://arxiv.org/abs/2410.18489 · HTML: https://mlsanity.com/paper/2410.18489/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 24 Oct 2024.

## Builds on (most cited first, 6 of 6)

- [Self-collaboration Code Generation via ChatGPT](https://mlsanity.com/paper/2304.07590/) (2023)
- [Towards Human-Bot Collaborative Software Architecting with ChatGPT](https://mlsanity.com/paper/2302.14600/) (2023)
- [Improving ChatGPT Prompt for Code Generation](https://mlsanity.com/paper/2305.08360/) (2023)
- [Analysis of ChatGPT on Source Code](https://mlsanity.com/paper/2306.00597/) (2023)
- [Coding by Design: GPT-4 empowers Agile Model Driven Development](https://mlsanity.com/paper/2310.04304/) (2023)
- [Bi-level Network Design for UAM Vertiport Allocation Using Activity-Based Transport Simulations](https://mlsanity.com/paper/2307.14731/) (2023)

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

- [Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale](https://mlsanity.com/paper/2511.08475/) (2025)

## Abstract (arXiv)

Leveraging Large Language Models (LLM) like GPT4 in the auto generation of code represents a significant advancement, yet it is not without its challenges. The ambiguity inherent in natural language descriptions of software poses substantial obstacles to generating deployable, structured artifacts. This research champions Model Driven Development (MDD) as a viable strategy to overcome these challenges, proposing an Agile Model Driven Development (AMDD) approach that employs GPT4 as a code generator. This approach enhances the flexibility and scalability of the code auto generation process and offers agility that allows seamless adaptation to changes in models or deployment environments. We illustrate this by modeling a multi agent Unmanned Vehicle Fleet (UVF) system using the Unified Modeling Language (UML), significantly reducing model ambiguity by integrating the Object Constraint Language (OCL) for code structure meta modeling, and the FIPA ontology language for communication semantics meta modeling. Applying GPT4 auto generation capabilities yields Java and Python code that is compatible with the JADE and PADE frameworks, respectively. Our thorough evaluation of the auto generated code verifies its alignment with expected behaviors and identifies enhancements in agent interactions. Structurally, we assessed the complexity of code derived from a model constrained solely by OCL meta models, against that influenced by both OCL and FIPA ontology meta models. The results indicate that the ontology constrained meta model produces inherently more complex code, yet its cyclomatic complexity remains within manageable levels, suggesting that additional meta model constraints can be incorporated without exceeding the high risk threshold for complexity.