Onnes: A Physics-Grounded Multi-Agent LLM Simulator for Cryogenic Fault Diagnosis in Quantum Computing Infrastructure
Quick Answer
Onnes is a physics-grounded digital twin simulator for dilution refrigerators, enhancing cryogenic fault diagnosis in quantum computing.
Quick Take
It achieves a classification accuracy of 99.0% using few-shot demonstrations, matching a supervised ML classifier, while maintaining a low false alarm rate of 6.4% on real hardware.
Key Points
- Onnes integrates real dilution-cooling data with a learned noise fingerprint.
- Zero-shot panel matches supervised classifier in fault detection.
- Classification accuracy improved from 68.5% to 99.0% with few-shot demonstrations.
- Agent detects faults within one polling interval, reducing false alarms.
- Real hardware tests show a 6.4% false alarm rate with 100% recall on physics faults.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Dilution refrigerators are the enabling infrastructure of superconducting quantum computers, yet their fault diagnosis is still dominated by threshold alarms that report that something is wrong, not what. We present Onnes, a physics-grounded digital-twin simulator of a dilution refrigerator (a forward physics model with a learned real-fridge noise fingerprint) that drives a live multi-agent LLM operations layer, and use it for a controlled head-to-head between a zero-shot LLM agent panel and a supervised ML classifier on cryogenic fault diagnosis. The twin couples a real dilution-cooling floor, a noise-and-correlation fingerprint learned from real BlueFors logs, and six physics-grounded fault classes, three engineered to overlap on temperature but separate on flow and pressure. Across a 1000-turn evaluation the zero-shot panel shows no significant difference from the classifier on detection but trails on classification, its errors concentrating on the confusable faults. Curated contrastive few-shot demonstrations and self-consistency voting then raise classification accuracy from 0.685 to 0.990, matching the supervised classifier (0.985) with no parameter updates and six labeled demonstrations; an ablation attributes the gain almost entirely to the demonstrations. Run as a continuous monitor across a nine-run fault-by-seed sweep, the agent catches every developing fault within one poll interval, and a confidence gate suppresses pre-onset false alarms whose rate is backend-dependent. As a first sim-to-real check, a detector trained purely on real BlueFors telemetry posts a real-hardware false-alarm rate of 6.4% and 100% recall on physics faults injected onto real held-out windows. All numbers are drawn verbatim from released run logs.
| Comments: | 18 pages, 14 figures, 10 tables. Code, data, and released run logs: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Quantum Physics (quant-ph) |
| Cite as: | arXiv:2607.05805 [cs.AI] |
| (or arXiv:2607.05805v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.05805 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Praneeth Narisetty [view email]
[v1]
Tue, 7 Jul 2026 03:57:21 UTC (816 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.