# Synergy of Large Language Model and Model Driven Engineering for Automated Development of Centralized Vehicular Systems

arXiv: https://arxiv.org/abs/2404.05508 · HTML: https://mlsanity.com/paper/2404.05508/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 14 references that are in the map.
- First posted on arXiv 8 Apr 2024.

## Builds on (most cited first, 1 of 1)

- [Towards Single-System Illusion in Software-Defined Vehicles -- Automated, AI-Powered Workflow](https://mlsanity.com/paper/2403.14460/) (2024)

## Built on by (most cited first, 7 of 7)

- [Adopting RAG for LLM-Aided Future Vehicle Design](https://mlsanity.com/paper/2411.09590/) (2024)
- [Multi-modal Summarization in Model-Based Engineering: Automotive Software Development Case Study](https://mlsanity.com/paper/2503.04506/) (2025)
- [Survey of GenAI for Automotive Software Development: From Requirements to Executable Code](https://mlsanity.com/paper/2507.15025/) (2025)
- [GenAI for Automotive Software Development: From Requirements to Wheels](https://mlsanity.com/paper/2507.18223/) (2025)
- [LLM-based Iterative Approach to Metamodeling in Automotive](https://mlsanity.com/paper/2503.05449/) (2025)
- [Metamodel-Guided Model Generation with Layered Constraints](https://mlsanity.com/paper/2510.25890/) (2025)
- [LLM-Based Approach for Enhancing Maintainability of Automotive Architectures](https://mlsanity.com/paper/2509.12798/) (2025)

## Abstract (arXiv)

We present a prototype of a tool leveraging the synergy of model driven engineering (MDE) and Large Language Models (LLM) for the purpose of software development process automation in the automotive industry. In this approach, the user-provided input is free form textual requirements, which are first translated to Ecore model instance representation using an LLM, which is afterwards checked for consistency using Object Constraint Language (OCL) rules. After successful consistency check, the model instance is fed as input to another LLM for the purpose of code generation. The generated code is evaluated in a simulated environment using CARLA simulator connected to an example centralized vehicle architecture, in an emergency brake scenario.