Metraipolis › archive › dc_dced2d188259
GURU: A Hierarchical Neuro-Symbolic Multi-Agent System for Verification-Aware Automation of Mission-Critical Digital Engineering and Operations — arXiv:2611.01001
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01001
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:59:28.370Z
- SHA-256 of the archived text
22acc8ddc4a3ee94343b4186dbd5bdd7555db748ff3a272596995899b739d9da- Stable URL of this page
https://metraipolis.com/documento/dc_dced2d188259
How to cite
GURU: A Hierarchical Neuro-Symbolic Multi-Agent System for Verification-Aware Automation of Mission-Critical Digital Engineering and Operations — arXiv:2611.01001 — arXiv (en), https://arxiv.org/abs/2611.01001 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dced2d188259 (Metraipolis archive dc_dced2d188259, sha256 22acc8ddc4a3ee94343b4186dbd5bdd7555db748ff3a272596995899b739d9da)
BibTeX
@misc{dcdced2d188259,
title = {GURU: A Hierarchical Neuro-Symbolic Multi-Agent System for Verification-Aware Automation of Mission-Critical Digital Engineering and Operations — arXiv:2611.01001},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01001},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dced2d188259; sha256 22acc8ddc4a3ee94343b4186dbd5bdd7555db748ff3a272596995899b739d9da},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01001. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
An AI can find a safe action faster than any human, but it must never decide what counts as safe. We present GURU, a hierarchical neuro-symbolic multi-agent system for mission-critical digital engineering and operations, built on one partition of authority: learned models propose, rank, and accelerate; a symbolic rules engine checks every consequential action against hard limits before it executes; and validated physics confirms and decides. GURU runs a workflow as a closed control loop, with Navigation, Action, and Planning agents sharing one Common Internal Language and one training factory. Nuclear, aviation, and national-security guidance now requires this pattern; a harnessed language model keeps the model at the center, GURU puts a validated reference there. In computational fluid dynamics, the workflow raised the converged-simulation rate on unseen aircraft geometries from under 1 percent to 74 percent over 100 single-attempt cases, ran 54 live cases to Mach 6 on three facilities, and an ablation put the symbolic layer at 13 points of boundary-layer capture. Knowledge-graph retrieval and role adapters raised ParaView control success from 55 to 75 percent. In space domain awareness, where a language model cannot be trusted to decide, a frozen self-supervised world model under validated propagation scored highest of five methods at conjunction risk, including fully fine-tuned language models, with several-times-lower seed variance: the trustworthy design gives up nothing in accuracy, and the recipe transferred to reactor anomaly detection. A radar-to-avoidance debris pipeline was demonstrated in stages on a 2026 reentry; the hierarchy coordinates simulated teams of 200 aircraft. Training scaled near-linearly past 1,000 Aurora nodes and ran at 8,000. The approach extends to a control-grade microreactor digital twin with validated physics, not a learned model, as the safety basis. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE); Multiagent Systems (cs.MA); Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2611.01001 — 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 2026-11-03T10:59:22.302Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).