Metraipolis › archive › dc_ea410907502f
Towards an Autonomous AI Steward for Large-Scale Physics Experiments: Integrating Causal Diagnostics, RAG, and Conformal Prediction — arXiv:2611.09298
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09298
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:34:01.747Z
- SHA-256 of the archived text
9d9bb6027a388a3f534773425e38e59bc25d8f5d9eefc6766412a239048c200b- Stable URL of this page
https://metraipolis.com/documento/dc_ea410907502f
How to cite
Towards an Autonomous AI Steward for Large-Scale Physics Experiments: Integrating Causal Diagnostics, RAG, and Conformal Prediction — arXiv:2611.09298 — arXiv (en), https://arxiv.org/abs/2611.09298 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea410907502f (Metraipolis archive dc_ea410907502f, sha256 9d9bb6027a388a3f534773425e38e59bc25d8f5d9eefc6766412a239048c200b)
BibTeX
@misc{dcea410907502f,
title = {Towards an Autonomous AI Steward for Large-Scale Physics Experiments: Integrating Causal Diagnostics, RAG, and Conformal Prediction — arXiv:2611.09298},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09298},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea410907502f; sha256 9d9bb6027a388a3f534773425e38e59bc25d8f5d9eefc6766412a239048c200b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09298. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-term particle physics experiments face critical operational challenges: monitoring non-stationary machine data streams and preserving tacit expert knowledge. We present the "Helmholtz Co-Pilot," a hybrid Multi-Agent System (MAS) acting as an autonomous experiment steward. The system can be triggered interactively by human operators or autonomously by an asynchronous causal diagnostics engine that runs independently of the MAS reasoning core. Continuously monitoring live hardware streams such as data acquisition and slow control, this engine performs dynamic causal discovery to trace cascading alarms back to their root causes and applies adaptive model selection to keep forecasts reliable across shifting machine states; upon detecting an anomaly, it hands a structured diagnostic report to the MAS. The reasoning layer itself relies on a high-throughput C++ core and a Python edge architecture orchestrating a directed acyclic graph (DAG) of specialized ReAct workers. It integrates a Retrieval-Augmented Generation (RAG) backbone for institutional memory and leverages conformal prediction to bound its evidence-based recommendations with mathematical coverage guarantees. This extended abstract outlines the architecture, the integration of software-enforced Human-in-the-Loop (HitL) guardrails, and ongoing shadow-testing within the KATRIN experiment. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.09298 — 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 2026-11-09T22:30:47.275Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).