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

• URL: http://arxiv.org/abs/2605.06607v3
• Date: Tue, 12 May 2026 22:57:53 GMT
• Title: AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
• Abstract summary: We present AI CFD Scientist, an open-source AI scientist for computational fluid dynamics.<n>It 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.
• Score: 1.7590081165362783
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• OpenAI4S: Code as Action, Science as Sessions [57.428071188574]
  We present OpenAI4S, an open-source scientific research agent built around the principle of emphCode as Action, Science as Sessions.<n>OpenAI4S combines a persistent computing runtime with research-session management orchestration is handled through structured tool calls.<n>We evaluate OpenAI4S on 36 research scenarios spanning retrosynthesis, molecular protein binder design, protein mutation, catalyst screening, and mineral spectroscopy.
  arXiv  Detail & Related papers  (2026-09-14T06:16:59Z)
• AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design [27.154390712714264]
  We present AgentFold, a framework that formulates folding-model development as a closed-loop search over executable code variants.<n>Under a matched computational budget, AgentFold improves the best lDDT by 7.5% over independent Codex proposals.<n>The resulting intervention traces reveal recurring empirical design patterns.
  arXiv  Detail & Related papers  (2026-08-27T07:38:16Z)
• Physics-Audited Agentic Discovery in Scientific Machine Learning [1.4632791454491378]
  Physics-Audited Agentic SciML (PA-SciML) is a verification-first workflow for agentic SciML discovery.<n>PA-SciML fixes a scoring evaluator before search, derives reviewable machine-checkable physics requirements, and searches for prescribed input ranges or measured load-history spans.<n>When enabled, the workflow also adds advisory numerical probes before training and tests one modeling change at a time to record which isolated edits are associated with score gains before reuse.
  arXiv  Detail & Related papers  (2026-07-08T13:10:35Z)
• From I/O to Code with Discovery Agent [103.88427301265669]
  We propose DIO-Agent, a discovery agent for IO2Code.<n>Our method frames IO2Code as an evolutionary search over discrete program space.<n>Extensive experiments show that DIO-Agent consistently outperforms both traditional program-by-example method and SOTA evolution-agent baselines.
  arXiv  Detail & Related papers  (2026-05-14T18:57:32Z)
• From Paper to Program: Accelerating Quantum Many-Body Algorithm Development via a Multi-Stage LLM-Assisted Workflow [4.866193347313755]
  Large language models (LLMs) can generate code rapidly but remain unreliable for scientific algorithms.<n>We introduce a multi-stage LLM-assisted workflow that separates theory extraction, formal specification, and code implementation.
  arXiv  Detail & Related papers  (2026-04-05T12:12:54Z)
• MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration [0.0]
  We present MatClaw, a code-first agent that writes and executes Python directly.<n>We show that MatClaw handles code generation reliably but struggles with tacit domain knowledge.<n>Our results demonstrate that the gap between guided and fully autonomous computational materials research is narrower than ever before.
  arXiv  Detail & Related papers  (2026-04-03T03:32:15Z)
• Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control [61.155940786140455]
  Reinforcement learning (RL) has shown promising results in active flow control (AFC)<n>Current AFC benchmarks rely on external computational fluid dynamics (CFD) solvers, are not fully differentiable, and provide limited 3D and multi-agent support.<n>We introduce FluidGym, the first standalone, fully differentiable benchmark suite for RL in AFC.
  arXiv  Detail & Related papers  (2026-01-21T14:13:44Z)
• GENIUS: An Agentic AI Framework for Autonomous Design and Execution of Simulation Protocols [32.505127447635864]
  GENIUS is an AI-agentic workflow that fuses a smart Quantum ESPRESSO knowledge graph with a tiered hierarchy of large language models supervised by a finite-state error-recovery machine.<n> GENIUS translates free-form human-generated prompts into validated input files that run to completion on $approx$80% of 295 diverse benchmarks, where 76% are autonomously repaired, with success decaying exponentially to a 7% baseline.<n>The framework democratizes electronic-structure DFT simulations by intelligently automating protocol generation, validation, and repair, opening large-scale screening and accelerating ICME design loops across academia and industry worldwide.
  arXiv  Detail & Related papers  (2025-12-06T11:28:35Z)
• INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers [61.84396402100827]
  We propose the Indirect Neural Corrector ($mathrmINC$), which integrates learned corrections into the governing equations.<n>$mathrmINC$ reduces the error amplification on the order of $t-1 + L$, where $t$ is the timestep and $L$ the Lipschitz constant.<n>We test $mathrmINC$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence.
  arXiv  Detail & Related papers  (2025-11-16T20:14:28Z)
• SciML Agents: Write the Solver, Not the Solution [69.5021018644143]
  We introduce two new datasets: a diagnostic dataset of adversarial "misleading" problems; and a large-scale benchmark of 1,000 diverse ODE tasks.<n>We evaluate open- and closed-source LLM models along two axes: (i) unguided versus guided prompting with domain-specific knowledge; and (ii) off-the-shelf versus fine-tuned variants.<n>Preliminary results indicate that careful prompting and fine-tuning can yield a specialized LLM agent capable of reliably solving simple ODE problems.
  arXiv  Detail & Related papers  (2025-09-12T02:53:57Z)
• PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics [62.93137406343609]
  We present our fluid simulator PICT, a differentiable pressure-implicit solver coded in PyTorch with Graphics-processing-unit (GPU) support.<n>We first verify the accuracy of both the forward simulation and our derived gradients in various established benchmarks.<n>We show that the gradients provided by our solver can be used to learn complicated turbulence models in 2D and 3D.
  arXiv  Detail & Related papers  (2025-05-22T17:55:10Z)
• MetaOpenFOAM: an LLM-based multi-agent framework for CFD [11.508919041921942]
  MetaOpenFOAM is a novel multi-agent collaborations framework. It aims to complete CFD simulation tasks with only natural language as input. It harnesses the power of MetaGPT's assembly line paradigm.
  arXiv  Detail & Related papers  (2024-07-31T04:01:08Z)
• Deep Surrogate for Direct Time Fluid Dynamics [44.62475518267084]
  Graph Neural Networks (GNN) can address the specificity of the irregular meshes commonly used in CFD simulations. We present our ongoing work to design a novel direct time GNN architecture for irregular meshes.
  arXiv  Detail & Related papers  (2021-12-16T10:08:20Z)
• PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics [89.81550748680245]
  We introduce a new differentiable physics benchmark called PasticineLab. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
  arXiv  Detail & Related papers  (2021-04-07T17:59:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.