Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches

TL;DR

This paper compares direct prompting and agentic LLM-based approaches for querying large automotive software models, demonstrating that agentic methods are more efficient and feasible for large models in industry settings.

Contribution

It introduces and evaluates an agentic LLM approach for software model querying, showing its practicality and efficiency over direct prompting in automotive contexts.

Findings

Agentic approach achieves comparable accuracy to direct prompting.

Agentic approach uses significantly fewer tokens, increasing efficiency.

Agentic approach is the only feasible method for large models in automotive industry.

Abstract

Large language models (LLMs) offer new opportunities for interacting with complex software artifacts, such as software models, through natural language. They present especially promising benefits for large software models that are difficult to grasp in their entirety, making traditional interaction and analysis approaches challenging. This paper investigates two approaches for leveraging LLMs to answer questions over software models: direct prompting, where the whole software model is provided in the context, and an agentic approach combining LLM-based agents with general-purpose file access tools. We evaluate these approaches using an Ecore metamodel designed for timing analysis and software optimization in automotive and embedded domains. Our findings show that while the agentic approach achieves accuracy comparable to direct prompting, it is significantly more efficient in terms of token usage. This efficiency makes the agentic approach particularly suitable for the automotive industry, where the large size of software models makes direct prompting infeasible, establishing LLM agents as not just a practical alternative but the only viable solution. Notably, the evaluation was conducted using small LLMs, which are more feasible to be executed locally - an essential advantage for meeting strict requirements around privacy, intellectual property protection, and regulatory compliance. Future work will investigate software models in diverse formats, explore more complex agent architectures, and extend agentic workflows to support not only querying but also modification of software models.