Metraipolis › archive › dc_c4f4a6f4e12e
Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant — arXiv:2608.15881
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15881
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T19:41:06.676Z
- SHA-256 of the archived text
8d52a6843382edf8053a75ce9945ad1121530c2fd63c3bbb9b2277c0ca8796df- Stable URL of this page
https://metraipolis.com/documento/dc_c4f4a6f4e12e
How to cite
Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant — arXiv:2608.15881 — arXiv (en), https://arxiv.org/abs/2608.15881 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4f4a6f4e12e (Metraipolis archive dc_c4f4a6f4e12e, sha256 8d52a6843382edf8053a75ce9945ad1121530c2fd63c3bbb9b2277c0ca8796df)
BibTeX
@misc{dcc4f4a6f4e12e,
title = {Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant — arXiv:2608.15881},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15881},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4f4a6f4e12e; sha256 8d52a6843382edf8053a75ce9945ad1121530c2fd63c3bbb9b2277c0ca8796df},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15881. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The Multiphysics Object-Oriented Simulation Environment (MOOSE) is an open-source finite-element framework for building multiphysics simulation applications. Using a multiphysics environment effectively demands specialized expertise, creating a barrier for many domain scientists and engineers. MOOSEnger, developed at Idaho National Laboratory (INL), is a domain-specific, tool-enabled AI agent built for the MOOSE Framework. This work extends MOOSEnger with a harness focused on locally-hosted models. The harness gives the agent a full pipeline: it retrieves contextual knowledge from the MOOSE repository, validates and diagnoses the resulting input through interaction with the simulation executable environment, and extracts and stores lessons in a persistent memory. The resulting framework is demonstrated on an engineering problem from the National Reactor Innovation Center Virtual Test Bed (VTB), illustrating its potential to support realistic multiphysics simulation workflows. Additionally, the agent performance is evaluated on different categories including diffusion, Navier--Stokes, phase field, plasticity, porous media flow, solid mechanics, transient heat transfer, and reactor mesh generation. Each category consists of 25 prompts/cases. We compare MOOSEnger-Gemma4 against MOOSEnger-GPT-5.2, alongside baseline Gemma4 and GPT-5.2 without agentic capabilities. MOOSEnger-GPT-5.2 shows a slight edge, achieving a 90\% success rate versus 76.5\% for MOOSEnger-Gemma4. The baseline models perform far worse, at just 5\% (GPT-5.2) and 0\% (Gemma4), underscoring the impact of the agentic harness. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Computational Engineering, Finance, and Science (cs.CE). Pagina del lavoro: https://arxiv.org/abs/2608.15881 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T19:02:44.134Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).