AI Insight
Researchers developed IteraSim RAG, an AI-powered system that automates the configuration of computational fluid dynamics simulations in OpenFOAM by combining large language models with multi-stage retrieval-augmented generation. The system uses query expansion, multiple retrieval strategies, and three specialized AI agents (Architect, InputWriter, and Reviewer) to generate the complex directory structures and parameter files required for CFD simulations. Testing on 28 benchmark cases achieved 77.9% mean retrieval coverage, with all reference configurations running successfully and the system successfully diagnosing and repairing corrupted cases.
Why it matters
This work addresses a major barrier to widespread adoption of open-source CFD software by non-specialists, potentially democratizing access to advanced fluid dynamics simulation tools. The multi-agent architecture and separated retrieval pathways represent a methodological advance over single-query RAG systems that could be applied to other complex scientific software configuration tasks.
Understand the Science
arXiv:2607.20346v1 Announce Type: cross
Abstract: Configuring a computational fluid dynamics (CFD) case in OpenFOAM requires assembling a multi-directory input deck of mutually consistent solver, discretisation and boundary-condition dictionaries — a task that remains a substantial barrier to non-specialist use of open-source CFD software. Large language models (LLMs) coupled with retrieval-augmented generation (RAG) can lower this barrier, but existing systems retrieve with a single flat query, apply one retrieval strategy to operationally distinct requests, and let a single agent both draft and review its own output. We present IteraSim RAG, a retrieval-augmented software back-end for automated OpenFOAM case generation built around these three limitations. An LLM first expands the query into physics, solver-keyword and troubleshooting variants, Reciprocal Rank Fusion then merges the resulting ranked lists, and Maximal Marginal Relevance re-ranks the fused candidates against an HNSW-indexed dense vector store. A deterministic keyword router dispatches tool-conditioned workflow queries and corpus-wide physics queries down separate retrieval paths, and generation is split across an Architect, an InputWriter and a Reviewer agent, backed by a static canonical-knowledge layer covering solver selection, turbulence closures, boundary conditions and finite-volume defaults. On an openly released 28-case benchmark spanning zero-shot setup, few-shot generalisation, single-parameter modifications and turbulence-model swaps, the pipeline attains a mean retrieval coverage of 77.9% (median 79.1%), with the parameter-modification category exceeding 90%. All six reference configurations run to completion on OpenFOAM v2506, and two synthetically corrupted cases are diagnosed and repaired within the bounded Reviewer loop using only the solver log and the canonical layer. The benchmark, scoring rubric and figure scripts are released for reproducibility.