Enregistré dans:
Détails bibliographiques
Auteurs principaux: Mazur, Lukasz, Petrovic, Nenad, Miranda, James Pontes, Radermacher, Ansgar, Rasche, Robert, Knoll, Alois
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.13171
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911007296716800
author Mazur, Lukasz
Petrovic, Nenad
Miranda, James Pontes
Radermacher, Ansgar
Rasche, Robert
Knoll, Alois
author_facet Mazur, Lukasz
Petrovic, Nenad
Miranda, James Pontes
Radermacher, Ansgar
Rasche, Robert
Knoll, Alois
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13171
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches
Mazur, Lukasz
Petrovic, Nenad
Miranda, James Pontes
Radermacher, Ansgar
Rasche, Robert
Knoll, Alois
Software Engineering
Artificial Intelligence
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.
title Querying Large Automotive Software Models: Agentic vs. Direct LLM Approaches
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2506.13171