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

arXiv: https://arxiv.org/abs/2506.13171 · HTML: https://mlsanity.com/paper/2506.13171/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 14 of its 34 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 14 of 14)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [ART: Automatic multi-step reasoning and tool-use for large language models](https://mlsanity.com/paper/2303.09014/) (2023)
- [Large Language Models for Software Engineering: Survey and Open Problems](https://mlsanity.com/paper/2310.03533/) (2023)
- [Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study](https://mlsanity.com/paper/2305.13062/) (2023)
- [Evaluating Open-Domain Question Answering in the Era of Large Language Models](https://mlsanity.com/paper/2305.06984/) (2023)
- [Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering](https://mlsanity.com/paper/2502.06193/) (2025)
- [Factuality of Large Language Models: A Survey](https://mlsanity.com/paper/2402.02420/) (2024)
- [On the use of Large Language Models in Model-Driven Engineering](https://mlsanity.com/paper/2410.17370/) (2024)
- [Evaluation of Semantic Answer Similarity Metrics](https://mlsanity.com/paper/2206.12664/) (2022)

## Built on by (most cited first, 3 of 3)

- [Survey of GenAI for Automotive Software Development: From Requirements to Executable Code](https://mlsanity.com/paper/2507.15025/) (2025)
- [Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering](https://mlsanity.com/paper/2603.26567/) (2026)
- [LLM-Driven Approach to Modeling Tool Interoperability in Automotive Domain](https://mlsanity.com/paper/2607.14659/) (2026)

## Abstract (arXiv)

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.