Paper page - AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents

Source: https://huggingface.co/papers/2605.06607 Published on May 12

·

Submitted byhttps://huggingface.co/LeoYML

Leo Yon May 14

Abstract

An AI system for computational fluid dynamics autonomously discovers physics corrections through vision-language verification and domain-specific code modification, outperforming general AI scientists in validity checking and scientific claim generation.

Recent LLM-based agents have closed substantial portions of the scientific discovery loop in software-only machine-learning research, in chemistry, and in biology. Extending the same loop to high-fidelity physical simulators is harder, because solver completion does not imply physical validity and many failure modes appear only in field-level imagery rather than in solver logs. We present AI CFD Scientist, an open-sourceAI scientistforcomputational fluid dynamics(CFD) that, to our knowledge, is the first to span literature-grounded ideation, validated execution, vision-based physics verification, source-code modification, and figure-grounded writing within a single inspectable workflow. Three coupled pathways cover parameter sweeps within a fixed solver, case-local C++ library compilation for new physical models, and open-ended hypothesis search against a reference comparator, all running onOpenFOAMthroughFoam-Agent. At the center of the framework is avision-language physics-verification gatethat inspects rendered flow fields before any result is accepted, rerun, or written into a manuscript. On five tasks under a sharedGPT-5.5backbone, AI CFD Scientist autonomously discovers aSpalart-Allmaras runtime correctionthat reduces lower-wall Cf RMSE againstDNSby 7.89% on the periodic hill at Reh=5600; under matched LLM cost, two strong general AI-scientist baselines (ARIS,DeepScientist) execute partial CFD workflows but lack the domain-specific validity gates needed to convert runs into defensible scientific claims; and a controlled planted-failure ablation shows that the vision-language gate detects 14 of 16 silent failures missed by solver-level checks. Code, prompts, and run artifacts are released at https://github.com/csml-rpi/cfd-scientist.

View arXiv pageView PDFGitHub3Add to collection

Get this paper in your agent:

hf papers read 2605\.06607

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.06607 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.06607 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.06607 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.