EUVIMEDEUVIMED entdecken
Crossref

Foam-Agent: A large language model-based multi-agent framework for automating computational fluid dynamics workflows

Ling Yue, Nithin Somasekharan, Tingwen Zhang, Yadi Cao, Zhangze Chen, Shimin Di, Shaowu Pan

Computer Methods in Applied Mechanics and Engineering · 2026-11 · 461 · 119271

DOI: 10.1016/j.cma.2026.119271 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods in Applied Mechanics and Engineering, 2026-11. Verfasst von Ling Yue und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Rensselaer Polytechnic Institute, Google LLC, US Department of Energy.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Rensselaer Polytechnic Institute
  • Google LLC
  • US Department of Energy

Zitieren

APA

Yue, L., Somasekharan, N., Zhang, T., Cao, Y., Chen, Z., Di, S., & Pan, S. (2026). Foam-Agent: A large language model-based multi-agent framework for automating computational fluid dynamics workflows. Computer Methods in Applied Mechanics and Engineering, 461, 119271. https://doi.org/10.1016/j.cma.2026.119271

Vancouver

Yue L, Somasekharan N, Zhang T, Cao Y, Chen Z, Di S, et al. Foam-Agent: A large language model-based multi-agent framework for automating computational fluid dynamics workflows. Computer Methods in Applied Mechanics and Engineering. 2026;461:119271. doi:10.1016/j.cma.2026.119271

BibTeX
@article{Yue2026,
  author = {Yue, Ling and Somasekharan, Nithin and Zhang, Tingwen and Cao, Yadi and Chen, Zhangze and Di, Shimin and Pan, Shaowu},
  title = {Foam-Agent: A large language model-based multi-agent framework for automating computational fluid dynamics workflows},
  journal = {Computer Methods in Applied Mechanics and Engineering},
  year = {2026},
  volume = {461},
  pages = {119271},
  doi = {10.1016/j.cma.2026.119271}
}
Kostenlos starten →