# Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows

arXiv: https://arxiv.org/abs/2505.04997 · HTML: https://mlsanity.com/paper/2505.04997/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 49 references that are in the map.
- First posted on arXiv 8 May 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning](https://mlsanity.com/paper/2402.04268/) (2024)
- [MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge](https://mlsanity.com/paper/2311.08166/) (2023)
- [MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalities](https://mlsanity.com/paper/2310.10445/) (2023)
- [MeLM, a generative pretrained language modeling framework that solves forward and inverse mechanics problems](https://mlsanity.com/paper/2306.17525/) (2023)
- [SciSciGPT: Advancing Human-AI Collaboration in the Science of Science](https://mlsanity.com/paper/2504.05559/) (2025)
- [Simulation of unsteady blood flows in a patient-specific compliant pulmonary artery with a highly parallel monolithically coupled fluid-structure interaction algorithm](https://mlsanity.com/paper/1810.04289/) (2018)

## Built on by (most cited first, 9 of 9)

- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Structured Knowledge and Reasoning](https://mlsanity.com/paper/2506.02019/) (2025)
- [MOOSEnger: A Simulation-Aware AI Agent Framework for the MOOSE Ecosystem](https://mlsanity.com/paper/2603.04756/) (2026)
- [FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills](https://mlsanity.com/paper/2607.21596/) (2026)
- [SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation](https://mlsanity.com/paper/2510.18551/) (2025)
- [Large language models for partial differential equation workflows](https://mlsanity.com/paper/2608.03600/) (2026)
- [ECAS: An Edge-Controlled Agentic System for Validation-Gated Scientific Application Execution](https://mlsanity.com/paper/2609.14211/) (2026)
- [ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations](https://mlsanity.com/paper/2609.32868/) (2026)
- [GPUPhysBench: Benchmarking Coding Agents for Correct and Efficient GPU Physics Simulation](https://mlsanity.com/paper/2609.35639/) (2026)

## Abstract (arXiv)

Computational fluid dynamics (CFD) has been the main workhorse of computational physics, yet its steep learning curve and fragmented, multi-stage workflow create significant barriers to entry. We present Foam-Agent, a multi-agent framework that leverages large language models (LLMs) to automate the end-to-end CFD workflow in OpenFOAM from a single natural-language prompt. Foam-Agent rests on three methodological contributions. First, a multi-index retrieval scheme organizes domain knowledge along four complementary structural dimensions and selects indices by workflow stage, sharpening retrieval precision over conventional single-index retrieval-augmented generation. Second, dependency-aware file generation is formulated as a topological traversal of the OpenFOAM case dependency graph, so that each configuration file is synthesized in the context of its already-generated predecessors, enforcing cross-file consistency. Third, a trajectory-conditioned reviewer loop iteratively repairs failed runs by conditioning each correction on the accumulated error-and-diagnosis trajectory of its own previous attempts, applying a minimal configuration edit that targets a reduced solver-error set. Around these contributions, six specialist agents span planning, meshing, file writing, execution, review, and visualization; Foam-Agent additionally exposes its capabilities through the Model Context Protocol as a deployment surface for external orchestrators. On FoamBench, Foam-Agent achieves an 88.2% execution success rate on the 110 Basic-tier tasks and 62.5% on the out-of-distribution Advanced tier, all without expert intervention. These results show how strategic harnessing of specialized multi-agent systems can reduce expertise barriers while preserving the rigor of solver-based simulation workflows.