Gradient-Aware AI Agents for Autonomous Turbulence Model Discovery via Differentiable CFD
physics.flu-dyn, cs.LG, cs.MA, physics.comp-ph
Submitted: 2026-11-11
Updated: 2026-11-11
Code: https://github.com/jax-ml/jax
Terminology
Sources
- Differentiable Hybrid Neural-CFD Modelling of Wall-Bounded Turbulence: Coupled Learning of Subgrid-Scale and Wall Closures
- Deep Learning-based Algebraic Reynolds Stress Closures for RANS Simulations of Turbulent Flows
- Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
- A Wall Function for Turbulent Boundary Layers under Rotation via Symbolic Regression
- Data-driven Symbolic Closure for Turbulence Modeling in the Lattice Boltzmann Framework
- CFD-driven symbolic regression of RANS transition models
- From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery
- Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap
- Kosmos: An AI Scientist for Autonomous Discovery
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- EvoPINN: Agentic Discovery of Executable Algorithms for Physics-Informed Neural Networks
- The AI Cosmologist I: An Agentic System for Automated Data Analysis
- Agentic AutoResearch forSpace Autonomy: An Auditable, LLM-Driven Research Agent for Aerospace Control Problems
- MetaOpenFOAM: an LLM-based multi-agent framework for CFD
- MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing
- SwarmFoam: An OpenFOAM Multi-Agent System Based on Multiple Types of Large Language Models
- PhyNiKCE: A Neurosymbolic Agentic Framework for Autonomous Computational Fluid Dynamics
- TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design
- Towards an AI Fluid Scientist: LLM-Powered Scientific Discovery in Experimental Fluid Mechanics
- Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control
Related papers
- Data-driven impeller model for efficient large eddy simulations of metastable von K'arm'an flows
- Numerical study of nitrogen oxides chemistry during plasma assisted combustion in a sequential combustor
- Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence
- Early onset of secondary shear instability in Kelvin-Helmholtz braids at high Reynolds number
- Rotational covariance, continuous spectrum and non-modal growth of three-dimensional planar weak viscous shock layers
- Deep Learning-based Algebraic Reynolds Stress Closures for RANS Simulations of Turbulent Flows