A Preliminary Assessment of Coding Agents for CFD Workflows

TL;DR

This paper explores the use of coding agents to automate CFD workflows in OpenFOAM, demonstrating improved task completion and efficiency with guided prompts and advanced language models.

Contribution

It introduces a lightweight configuration for coding agents to enhance CFD workflow automation and evaluates their performance on benchmark tasks using different language models.

Findings

Prompt guidance increases execution success rates.

Advanced models like GPT-5.2 improve mesh generation.

Coding agents can automate CFD tasks with minimal setup.

Abstract

We investigate the use of tool-using coding agents to automate end-to-end workflows in the open-source CFD package OpenFOAM. Building on general-purpose coding agent interfaces, we introduce a lightweight configuration that guides an agent toward tutorial reuse and log-driven repair to improve case setup and execution. We evaluate this approach on the FoamBench-Advanced benchmark, covering both tutorial-derivative and planar 2D obstacle-flow tasks. For tutorial-derivative cases, prompt guidance dramatically increases execution completion rates and reduces unnecessary tool calls. For obstacle-flow cases, stronger language models such as GPT-5.2 markedly improve mesh generation and overall task completion compared to earlier models. Our findings show that coding agents can correctly execute a range of CFD simulations with minimal configuration and that model capability significantly influences performance on tasks requiring geometry and mesh creation. These results suggest that coding agents have practical utility for automating portions of CFD workflows while highlighting areas that require further investigation.