Generating Automotive Code: Large Language Models for Software Development and Verification in Safety-Critical Systems

2025-06-04

AI Summary

To address the challenge of balancing functional safety compliance and development efficiency in safety-critical automotive software, this paper proposes the first ISO 26262–oriented, safety-enhanced LLM engineering framework. The framework integrates large language models (LLMs), static code analysis, test-driven development (TDD), and a simulation-based feedback loop to enable automated generation and systematic safety alignment of C++ embedded code. A novel multi-dimensional LLM benchmarking methodology is introduced to rigorously evaluate and ensure the reliability and certifiability of generated code. Evaluated on an adaptive cruise control (ACC) system, the framework produces code fully compliant with ASIL-B requirements under ISO 26262:2018, passing all functional safety verification and validation activities. Empirical results demonstrate substantial improvements in development productivity without compromising safety assurance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness
• Computer Vision: Large Vision Models

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Developing safety-critical automotive software presents significant challenges due to increasing system complexity and strict regulatory demands. This paper proposes a novel framework integrating Generative Artificial Intelligence (GenAI) into the Software Development Lifecycle (SDLC). The framework uses Large Language Models (LLMs) to automate code generation in languages such as C++, incorporating safety-focused practices such as static verification, test-driven development and iterative refinement. A feedback-driven pipeline ensures the integration of test, simulation and verification for compliance with safety standards. The framework is validated through the development of an Adaptive Cruise Control (ACC) system. Comparative benchmarking of LLMs ensures optimal model selection for accuracy and reliability. Results demonstrate that the framework enables automatic code generation while ensuring compliance with safety-critical requirements, systematically integrating GenAI into automotive software engineering. This work advances the use of AI in safety-critical domains, bridging the gap between state-of-the-art generative models and real-world safety requirements.

Problem

• Automating code generation for safety-critical automotive systems using LLMs
• Integrating GenAI into SDLC with static verification and test-driven development
• Ensuring compliance with safety standards through feedback-driven verification

Innovation

• LLMs automate C++ code generation with safety practices
• Feedback pipeline integrates testing and verification for compliance
• Benchmarking ensures optimal LLM selection for reliability