LLM-Based Approach for Enhancing Maintainability of Automotive Architectures

2025-09-16

AI Summary

Automotive systems face significant challenges in maintenance, updates, and scalability due to hardware heterogeneity, proliferation of software components, and lengthy regulatory compliance processes. To address these issues, this paper introduces, for the first time, large language models—specifically GPT-4o—into automotive architecture engineering. We propose an automated decision-support framework targeting hardware abstraction, interface compatibility verification, and architectural evolution. Leveraging joint natural language understanding and code semantic analysis, our method performs update compliance assessment, cross-version interface matching, and generates interpretable architectural refactoring recommendations. Evaluated on three early-stage industrial case studies, the approach substantially reduces manual analysis effort, accurately identifies compatibility risks, and produces optimization proposals compliant with functional safety standards (e.g., ISO 26262) and AUTOSAR specifications. This work establishes a novel paradigm for sustainable evolution of intelligent automotive systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Hardware-aware ML
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

There are many bottlenecks that decrease the flexibility of automotive systems, making their long-term maintenance, as well as updates and extensions in later lifecycle phases increasingly difficult, mainly due to long re-engineering, standardization, and compliance procedures, as well as heterogeneity and numerosity of devices and underlying software components involved. In this paper, we explore the potential of Large Language Models (LLMs) when it comes to the automation of tasks and processes that aim to increase the flexibility of automotive systems. Three case studies towards achieving this goal are considered as outcomes of early-stage research: 1) updates, hardware abstraction, and compliance, 2) interface compatibility checking, and 3) architecture modification suggestions. For proof-of-concept implementation, we rely on OpenAI's GPT-4o model.

Problem

• Addressing bottlenecks in automotive system flexibility
• Automating tasks to improve long-term maintenance and updates
• Enhancing architecture maintainability through LLM-based solutions

Innovation

• LLM-based automation for automotive systems
• GPT-4o implementation for architecture tasks
• Hardware abstraction and compatibility checking automation