AICFDScientist is an open-source multi-agent framework for end-to-end CFD discovery built on OpenFOAM. The system combines literature-aware ideation, validated simulation setup generation, automated execution, mesh-independence checking, simulator source-code modification, VLM-based physics verification, reference-data alignment, and figure-grounded manuscript writing within a unified workflow.</p>\n<p>The framework supports three pathways:</p>\n<ol>\n<li>Regular CFD experimentation and parameter sweeps</li>\n<li>Simulator source-code modification for custom physical models</li>\n<li>Open-ended discovery loops for iterative model exploration</li>\n</ol>\n","updatedAt":"2026-05-15T00:55:29.312Z","author":{"_id":"66739484a660dfbb2643eb3d","avatarUrl":"/avatars/c9a6c6a1e295e448dacfccb1a2860e8a.svg","fullname":"Leo Y","name":"LeoYML","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":5,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7709901332855225},"editors":["LeoYML"],"editorAvatarUrls":["/avatars/c9a6c6a1e295e448dacfccb1a2860e8a.svg"],"reactions":[],"isReport":false}},{"id":"6a067a792a40e5696f893582","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":355,"isUserFollowing":false},"createdAt":"2026-05-15T01:44:25.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [Towards grounded autonomous research: an end-to-end LLM mini research loop on published computational physics](https://huggingface.co/papers/2604.12198) (2026)\n* [PRBench: End-to-end Paper Reproduction in Physics Research](https://huggingface.co/papers/2603.27646) (2026)\n* [ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration](https://huggingface.co/papers/2605.03042) (2026)\n* [COMPOSITE-Stem](https://huggingface.co/papers/2604.09836) (2026)\n* [MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration](https://huggingface.co/papers/2604.02688) (2026)\n* [AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation](https://huggingface.co/papers/2603.20986) (2026)\n* [AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs](https://huggingface.co/papers/2604.08590) (2026)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"<p>This is an automated message from the <a href=\"https://huggingface.co/librarian-bots\">Librarian Bot</a>. I found the following papers similar to this paper. </p>\n<p>The following papers were recommended by the Semantic Scholar API </p>\n<ul>\n<li><a href=\"https://huggingface.co/papers/2604.12198\">Towards grounded autonomous research: an end-to-end LLM mini research loop on published computational physics</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2603.27646\">PRBench: End-to-end Paper Reproduction in Physics Research</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2605.03042\">ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.09836\">COMPOSITE-Stem</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.02688\">MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2603.20986\">AutoMOOSE: An Agentic AI for Autonomous Phase-Field Simulation</a> (2026)</li>\n<li><a href=\"https://huggingface.co/papers/2604.08590\">AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs</a> (2026)</li>\n</ul>\n<p> Please give a thumbs up to this comment if you found it helpful!</p>\n<p> If you want recommendations for any Paper on Hugging Face checkout <a href=\"https://huggingface.co/spaces/librarian-bots/recommend_similar_papers\">this</a> Space</p>\n<p> You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: <code><span class=\"SVELTE_PARTIAL_HYDRATER contents\" data-target=\"UserMention\" data-props=\"{"user":"librarian-bot"}\"><span class=\"inline-block\"><span class=\"contents\"><a href=\"/librarian-bot\">@<span class=\"underline\">librarian-bot</span></a></span> </span></span> recommend</code></p>\n","updatedAt":"2026-05-15T01:44:25.558Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":355,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7189992666244507},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.06607","authors":[{"_id":"6a066ebcb1a8cbabc9f097a9","name":"Nithin Somasekharan","hidden":false},{"_id":"6a066ebcb1a8cbabc9f097aa","name":"Rabi Pathak","hidden":false},{"_id":"6a066ebcb1a8cbabc9f097ab","name":"Manushri Dhanakoti","hidden":false},{"_id":"6a066ebcb1a8cbabc9f097ac","name":"Tingwen Zhang","hidden":false},{"_id":"6a066ebcb1a8cbabc9f097ad","name":"Ling Yue","hidden":false},{"_id":"6a066ebcb1a8cbabc9f097ae","name":"Andy Zhu","hidden":false},{"_id":"6a066ebcb1a8cbabc9f097af","name":"Shaowu Pan","hidden":false}],"publishedAt":"2026-05-12T00:00:00.000Z","submittedOnDailyAt":"2026-05-14T00:00:00.000Z","title":"AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents","submittedOnDailyBy":{"_id":"66739484a660dfbb2643eb3d","avatarUrl":"/avatars/c9a6c6a1e295e448dacfccb1a2860e8a.svg","isPro":false,"fullname":"Leo Y","user":"LeoYML","type":"user","name":"LeoYML"},"summary":"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-source AI scientist for computational 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 on OpenFOAM through Foam-Agent. At the center of the framework is a vision-language physics-verification gate that inspects rendered flow fields before any result is accepted, rerun, or written into a manuscript. On five tasks under a shared GPT-5.5 backbone, AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction that reduces lower-wall Cf RMSE against DNS by 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.","upvotes":1,"discussionId":"6a066ebcb1a8cbabc9f097b0","githubRepo":"https://github.com/csml-rpi/AI-CFD-Scientist","githubRepoAddedBy":"user","ai_summary":"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.","ai_keywords":["AI scientist","computational fluid dynamics","vision-language physics-verification gate","OpenFOAM","Foam-Agent","Spalart-Allmaras runtime correction","DNS","GPT-5.5","ARIS","DeepScientist"],"githubStars":3,"organization":{"_id":"6459af765e44a749d5a5b7a2","name":"Rensselaer-Polytechnic-Institute","fullname":"Rensselaer Polytechnic Institute","avatar":"https://www.gravatar.com/avatar/17efab27a0d875b715ed934170a15825?d=retro&size=100"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"66739484a660dfbb2643eb3d","avatarUrl":"/avatars/c9a6c6a1e295e448dacfccb1a2860e8a.svg","isPro":false,"fullname":"Leo Y","user":"LeoYML","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6459af765e44a749d5a5b7a2","name":"Rensselaer-Polytechnic-Institute","fullname":"Rensselaer Polytechnic Institute","avatar":"https://www.gravatar.com/avatar/17efab27a0d875b715ed934170a15825?d=retro&size=100"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.06607.md"}">
AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
Published on May 12
· Submitted by Leo Y on 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.
AI-generated summary
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-source AI scientist for computational 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 on OpenFOAM through Foam-Agent. At the center of the framework is a vision-language physics-verification gate that inspects rendered flow fields before any result is accepted, rerun, or written into a manuscript. On five tasks under a shared GPT-5.5 backbone, AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction that reduces lower-wall Cf RMSE against DNS by 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.
Community
AICFDScientist is an open-source multi-agent framework for end-to-end CFD discovery built on OpenFOAM. The system combines literature-aware ideation, validated simulation setup generation, automated execution, mesh-independence checking, simulator source-code modification, VLM-based physics verification, reference-data alignment, and figure-grounded manuscript writing within a unified workflow.
The framework supports three pathways:
- Regular CFD experimentation and parameter sweeps
- Simulator source-code modification for custom physical models
- Open-ended discovery loops for iterative model exploration
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.06607 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.06607 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.06607 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.