# A Multi-Agent LLM Framework for Design Space Exploration in Autonomous Driving Systems

arXiv: https://arxiv.org/abs/2512.08476 · HTML: https://mlsanity.com/paper/2512.08476/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Large language models for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 5 of its 35 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Placed in

- End-to-end autonomous driving / [Large language models for driving](https://mlsanity.com/driving/large-language-models-for-driving/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 5 of 5)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024)
- [IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction](https://mlsanity.com/paper/2408.10455/) (2024)
- [ros2_tracing: Multipurpose Low-Overhead Framework for Real-Time Tracing of ROS 2](https://mlsanity.com/paper/2201.00393/) (2022)

## Built on by (most cited first, 1 of 1)

- [REARL: A Closed-loop Autonomous Driving Simulation Enhancement Framework with Real Traffic Data and Large Language Models](https://mlsanity.com/paper/2609.19903/) (2026)

## Abstract (arXiv)

Designing autonomous driving systems requires efficient exploration of large hardware/software configuration spaces under diverse environmental conditions, e.g., with varying traffic, weather, and road layouts. Traditional design space exploration (DSE) approaches struggle with multi-modal execution outputs and complex performance trade-offs, and often require human involvement to assess correctness based on execution outputs. This paper presents a multi-agent, large language model (LLM)-based DSE framework, which integrates multi-modal reasoning with 3D simulation and profiling tools to automate the interpretation of execution outputs and guide the exploration of system designs. Specialized LLM agents are leveraged to handle user input interpretation, design point generation, execution orchestration, and analysis of both visual and textual execution outputs, which enables identification of potential bottlenecks without human intervention. A prototype implementation is developed and evaluated on a robotaxi case study (an SAE Level 4 autonomous driving application). Compared with a genetic algorithm baseline, the proposed framework identifies more Pareto-optimal, cost-efficient solutions with reduced navigation time under the same exploration budget. Experimental results also demonstrate the efficiency of the adoption of the LLM-based approach for DSE. We believe that this framework paves the way to the design automation of autonomous driving systems.