MetaOpenFOAM 2.0: Automating CFD Workflows

• MetaOpenFOAM 2.0 is an LLM-driven system that automates CFD simulation and post-processing workflows through a modular, multi-agent pipeline.
• It employs chain-of-thought decomposition and an iterative verification loop to break down complex tasks and ensure numerical and physical accuracy.
• Benchmark results demonstrate improved executability, reduced token usage, and lower costs, making it ideal for rapid, cost-efficient CFD prototyping.

MetaOpenFOAM 2.0 is a LLM-driven system for automating computational fluid dynamics (CFD) simulation and post-processing workflows based on OpenFOAM. It integrates chain-of-thought (COT) decomposition, retrieval-augmented generation (RAG), and iterative verification mechanisms to convert natural language requirements into executable CFD tasks for both simulations and complex post-processing. MetaOpenFOAM 2.0 demonstrates improved automation, accuracy, and cost-efficiency compared to previous approaches, significantly outperforming its predecessor across a standardized benchmark suite (Chen et al., 1 Feb 2025).

1. System Architecture

MetaOpenFOAM 2.0 features a multi-agent, modular pipeline that orchestrates automation of CFD workflows in the following stages:

• Natural-Language Parser: Normalizes free-form user requirements for downstream processing.
• Retrieval-Augmented Generation (RAG): Embeds the normalized requirement in a FAISS vector store, retrieving the top-$k$ OpenFOAM tutorial/case exemplars to ground subsequent reasoning.
• QDCOT Decomposer: Applies a hierarchical, two-stage question decomposition, first partitioning the requirement into coarse tasks (simulation and post-processing), then further dividing into granular subtasks specific to OpenFOAM or post-processing routines.
• Iterative COT (ICOT) Loop: For each subtask, iterates between three agents—InputWriter (generates/edits inputs/scripts), Runner (executes shell commands, captures outputs/errors), and Reviewer (inspects, comments, triggers rewrites)—until the subtask is resolved or a maximum iteration cap is reached.
• LLM-Assisted Final Verifier: Checks global physical and numerical validity, verifying satisfaction of user intent, boundary conditions, flow characteristics, convergence, and physical consistency.

The backbone of the system is concisely presented in Algorithm 1:

$(φ)$8

Here, $φ$ denotes task-level decomposition, $ψ$ subtask-level decomposition, and $V$ the final verification step (Chen et al., 1 Feb 2025).

2. Chain-of-Thought (COT) Decomposition

COT in MetaOpenFOAM 2.0 is realized as a structured, two-level hierarchy:

• Task-Level Decomposition $(φ)$: The requirement $Q$ is divided into $\{T_1, T_2\}$ where $T_1$ is “CFD simulation,” $T_2$ is “CFD post-processing.”
• Subtask-Level Decomposition $(ψ)$: Each $φ$0 maps to an ordered list $φ$1, e.g., $φ$2write controlDict, run pimpleFoam, check convergence$φ$3 and $φ$4run post-process commands, convert to VTK, run Python script$φ$5.

This explicit task-subtask breakdown, summarized as $φ$6, localizes computational and logical errors and mitigates cross-domain propagation between simulators, shell, and Python subsystems.

3. Iterative Verification and Correction Mechanism

Each subtask $φ$7 undergoes an Iterative Chain-of-Thought (ICOT) refinement loop defined as follows:

Given an initial state $φ$8, at each iteration $φ$9: $ψ$0

The loop continues until either $ψ$1 or $ψ$2 saturates $ψ$3 (default 10). Upon subtask completion, the LLM-driven FinalVerifier checks assembled outputs for requirement satisfaction, physical and numerical accuracy (e.g., $ψ$4 range, convergence), and boundary consistency. Detected errors route the process back to the offending subtask (Chen et al., 1 Feb 2025).

4. Benchmarking and Metrics

MetaOpenFOAM 2.0’s assessment employs a 13-task benchmark suite with seven simulation cases (e.g., incompressible RANS flows, DNS-HIT, reactingFoam) and six post-processing cases (extractions like max $ψ$5, TKE, plus visualization outputs).

Key metrics include:

• Executability $ψ$6: Ranging from simulation-only completion (0–3), through mix CLI/Python post-processing (4–5), numerical/physical validation (6), to human-judged flawless execution (7).
• Cost Metrics: Total agent iterations $ψ$7, token usage $ψ$8, and USD-equivalent cost (average \$0.15/case).
• Pass@k: Fraction of $ψ$9 generated samples with $V$0 among the top-$V$1, e.g., for $V$2, $V$3 represents single-shot success: $V$4

This evaluation framework quantifies both accuracy and cost-efficiency (Chen et al., 1 Feb 2025).

5. Experimental Performance and Ablation Studies

MetaOpenFOAM 2.0 demonstrates significant gains over MetaOpenFOAM 1.0 in all core metrics. Averaged across 13 tasks and 10 runs, the results are:

Metric	MetaOpenFOAM 1.0	MetaOpenFOAM 2.0
Executability $V$5	2.1/7	6.3/7
Pass@1 (%)	0%	86.9%
Avg. token usage	47,426	36,448
Avg. cost (USD)	\$V$60.15
Avg. iterations	6.7	3.7

Ablation results underscore that both COT decompositions and ICOT iterative correction are essential. Removal of CLI/Python post-processing in the QDCOT ablations drops $V$7 to around 2.1, while omitting the ICOT reviewer loop reduces $V$8 to 1.4. Full system synergy provides a $V$9+4 increase in $(φ)$0 over monolithic (non-modular) approaches. Simulation-only tasks typically reach $(φ)$1 in near-minimal ICOT iterations, whereas more challenging DNS or complex post-processing tasks achieve lower, but still robust scores (Chen et al., 1 Feb 2025).

6. Post-Training Scaling Laws

The system exhibits two post-training scaling regularities:

• Executability versus QDCOT steps $(φ)$2: $(φ)$3; token usage also increases sublinearly $(φ)$4.
• Executability versus ICOT iterations $(φ)$5: $(φ)$6, with $(φ)$$7.</li> </ul> <p>These trends <a href="https://www.emergentmind.com/topics/additive-parallel-correction" title="" rel="nofollow" data-turbo="false" class="assistant-link" x-data x-tooltip.raw="">parallel</a> those observed in general LLM post-training scaling, enabling trade-offs between accuracy and computational (token) cost (<a href="/papers/2502.00498" title="" rel="nofollow" data-turbo="false" class="assistant-link" x-data x-tooltip.raw="">Chen et al., 1 Feb 2025</a>).</p> <h2 class='paper-heading' id='implications-limitations-and-future-prospects'>7. Implications, Limitations, and Future Prospects</h2> <p>MetaOpenFOAM 2.0 abstracts CFD task configuration and post-processing behind a natural-language interface, facilitating access for non-expert users across aerospace, energy, and biological fluid mechanics. By automating error localization through COT and ensuring reliability via ICOT, the system reduces token usage by approximately 23$$0.15/case) prototyping for parameter studies.

  Current limitations include an assumption of pre-meshed geometries, a lack of full pre-processing automation (mesh generation), and constraints to single-physics OpenFOAM examples. Multi-physics coupling and real-time physics selection are not addressed.

  Planned future developments include:

  • Integration of mesh generation and geometry parametricization within the COT framework.
  • Extensions to multi-phase and fluid–structure interaction solvers.
  • Use of reinforcement learning fine-tuning on CFD case libraries for improved COT efficiency.
  • Development of lightweight, domain-specific LLMs to lower operational costs.

  MetaOpenFOAM 2.0’s documented methodology and codebase are available at https://github.com/Terry-cyx/MetaOpenFOAM (Chen et al., 1 Feb 2025).