A Closed-Loop Multi-Agent Framework for Aerodynamics-Aware Automotive Styling Design

TL;DR

This paper introduces a novel multi-agent framework driven by large language models that automates the early-stage automotive design process, integrating creative concept generation with rapid aerodynamic validation to accelerate development.

Contribution

It presents a unified system combining creative design and fast aerodynamic validation, replacing traditional CFD simulations with surrogate models within an automated workflow.

Findings

Automates concept generation and rendering from fuzzy requirements.

Provides near-instantaneous aerodynamic predictions using surrogate models.

Streamlines early-stage automotive design process.

Abstract

The core challenge in automotive exterior design is balancing subjective aesthetics with objective aerodynamic performance while dramatically accelerating the development cycle. To address this, we propose a novel, LLM-driven multi-agent framework that automates the end-to-end workflow from ambiguous requirements to 3D concept model performance validation. The workflow is structured in two stages: conceptual generation and performance validation. In the first stage, agents collaborate to interpret fuzzy design requirements, generate concept sketches, and produce photorealistic renderings using diffusion models. In the second stage, the renderings are converted to 3D point clouds, where a Drag Prediction Agent, built upon a lightweight surrogate model, provides near-instantaneous predictions of the drag coefficient and pressure fields, replacing time-consuming CFD simulations. The primary contribution of this work is the seamless integration of creative generation with a rapid engineering validation loop within a unified, automated system, which provides a new paradigm for efficiently balancing creative exploration with engineering constraints in the earliest stages of design.