A six-agent LLM system automates end-to-end Abaqus FEA for solid mechanics problems and achieves 86% success on 50 test cases.
hub
Metaopenfoam: an llm-based multi-agent framework for cfd
14 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
14
Pith papers citing it
1
external citations · external index
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
SCICONVBENCH is a new benchmark evaluating LLMs on multi-turn disambiguation and inconsistency resolution for task formulation in computational science, with frontier models reaching only 52.7% success on fluid mechanics disambiguation cases.
A new Intent Fidelity Score and refinement loop verify that LLM-generated simulation code matches the intended PDEs, improving performance on a 220-case benchmark where execution alone fails to ensure correctness.
AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction reducing lower-wall Cf RMSE by 7.89% on the periodic hill at Reh=5600 while using a vision-language gate to detect 14 of 16 silent failures missed by solver checks.
A constrained LLM front-end for FEniCS multi-physics simulations dispatches to human-written templates and achieves 100% valid parses plus 90-100% geometry success on benchmarks while avoiding LLM-generated solver code.
SIGA is a coding-agent adapter using retrieval, procedural memory, and validation gates that raises success rate on GEOS from 0.720 to 0.789 while cutting variance 16x and matching expert quality in minutes instead of hours.
An agentic AI workflow automates end-to-end SPH debris flow simulations via tool orchestration, multimodal inputs, and human-in-the-loop, demonstrating viability for meshless computational mechanics.
COSMO-Agent trains LLMs via tool-augmented RL and a multi-constraint reward to close the CAD-CAE loop, with experiments showing small open-source models outperforming larger ones on feasibility and stability for 25 component categories.
ALL-FEM fine-tunes LLMs on a corpus of verified FEniCS scripts and uses multi-agent workflows to automate finite element code generation, achieving 71.79% success on 39 benchmarks across elasticity, flow, and coupled problems.
CFDLLMBench is a new benchmark suite with CFDQuery, CFDCodeBench, and FoamBench to evaluate LLMs on graduate-level CFD knowledge, numerical reasoning, and context-dependent code implementation.
LLM assistance can help newcomers build multiphysics simulations, but converged, plausible-looking results still hide incorrect physics that the AI will defend with coherent reasoning.
TurboAgent uses an LLM as coordinator for specialized agents to autonomously generate, predict, optimize, and validate turbomachinery designs, achieving R² > 0.91 agreement with CFD on a transonic compressor and 1.61% efficiency gains.
COSMO-Agent is a tool-augmented RL agent that trains LLMs to complete closed-loop CAD-CAE optimization using a multi-constraint reward and an industry dataset of 25 component categories, improving small models over larger ones.
citing papers explorer
-
A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems
A six-agent LLM system automates end-to-end Abaqus FEA for solid mechanics problems and achieves 86% success on 50 test cases.
-
SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science
SCICONVBENCH is a new benchmark evaluating LLMs on multi-turn disambiguation and inconsistency resolution for task formulation in computational science, with frontier models reaching only 52.7% success on fluid mechanics disambiguation cases.
-
Your Simulation Runs but Solves the Wrong Physics: PDE-Grounded Intent Verification for LLM-Generated Multiphysics Simulation Code
A new Intent Fidelity Score and refinement loop verify that LLM-generated simulation code matches the intended PDEs, improving performance on a 220-case benchmark where execution alone fails to ensure correctness.
-
AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction reducing lower-wall Cf RMSE by 7.89% on the periodic hill at Reh=5600 while using a vision-language gate to detect 14 of 16 silent failures missed by solver checks.
-
A Constrained Natural-Language Interface for Variational Multi-Physics Finite Element Simulations in FEniCS
A constrained LLM front-end for FEniCS multi-physics simulations dispatches to human-written templates and achieves 100% valid parses plus 90-100% geometry success on benchmarks while avoiding LLM-generated solver code.
-
Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters
SIGA is a coding-agent adapter using retrieval, procedural memory, and validation gates that raises success rate on GEOS from 0.720 to 0.789 while cutting variance 16x and matching expert quality in minutes instead of hours.
-
Agentic AI for Particle-Based Simulation: Automating SPH Workflows for Debris Flow Modeling
An agentic AI workflow automates end-to-end SPH debris flow simulations via tool orchestration, multimodal inputs, and human-in-the-loop, demonstrating viability for meshless computational mechanics.
-
COSMO-Agent: Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration
COSMO-Agent trains LLMs via tool-augmented RL and a multi-constraint reward to close the CAD-CAE loop, with experiments showing small open-source models outperforming larger ones on feasibility and stability for 25 component categories.
-
ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methods
ALL-FEM fine-tunes LLMs on a corpus of verified FEniCS scripts and uses multi-agent workflows to automate finite element code generation, achieving 71.79% success on 39 benchmarks across elasticity, flow, and coupled problems.
-
CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics
CFDLLMBench is a new benchmark suite with CFDQuery, CFDCodeBench, and FoamBench to evaluate LLMs on graduate-level CFD knowledge, numerical reasoning, and context-dependent code implementation.
-
False Summit and Silent Drift: A Failure Taxonomy and Efficiency Analysis of LLM-Assisted Multiphysics Simulation in an Open-Source Framework
LLM assistance can help newcomers build multiphysics simulations, but converged, plausible-looking results still hide incorrect physics that the AI will defend with coherent reasoning.
-
TurboAgent: An LLM-Driven Autonomous Multi-Agent Framework for Turbomachinery Aerodynamic Design
TurboAgent uses an LLM as coordinator for specialized agents to autonomously generate, predict, optimize, and validate turbomachinery designs, achieving R² > 0.91 agreement with CFD on a transonic compressor and 1.61% efficiency gains.
-
Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration
COSMO-Agent is a tool-augmented RL agent that trains LLMs to complete closed-loop CAD-CAE optimization using a multi-constraint reward and an industry dataset of 25 component categories, improving small models over larger ones.
- PDE-Agents: An LLM-Orchestrated Multi-Agent Framework for Automated Finite Element Simulations with Knowledge Graph-Augmented Reasoning