7 papers
Req2Road: A GenAI Pipeline for SDV Test Artifact Generation and On-Vehicle Execution
Denesa Zyberaj, Lukasz Mazur, Pascal Hirmer +3
Testing functionality in Software-Defined Vehicles is challenging because requirements are written in natural language, specifications combine text, tables, and diagrams, while tes…
LLM-Based Approach for Enhancing Maintainability of Automotive Architectures
Nenad Petrovic, Lukasz Mazur, Alois Knoll
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 incr…
GenAI-based test case generation and execution in SDV platform
Denesa Zyberaj, Lukasz Mazur, Nenad Petrovic +5
This paper introduces a GenAI-driven approach for automated test case generation, leveraging Large Language Models and Vision-Language Models to translate natural language requirem…
Hallucination in LLM-Based Code Generation: An Automotive Case Study
Marc Pavel, Nenad Petrovic, Lukasz Mazur +3
Large Language Models (LLMs) have shown significant potential in automating code generation tasks offering new opportunities across software engineering domains. However, their pra…
Survey of GenAI for Automotive Software Development: From Requirements to Executable Code
Nenad Petrovic, Vahid Zolfaghari, Andre Schamschurko +10
Adoption of state-of-art Generative Artificial Intelligence (GenAI) aims to revolutionize many industrial areas by reducing the amount of human intervention needed and effort for h…
Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches
Lukasz Mazur, Nenad Petrovic, James Pontes Miranda +3
Large language models (LLMs) offer new opportunities for interacting with complex software artifacts, such as software models, through natural language. They present especially pro…