mlsanityData to 7 Oct 2026

Toward a Fully Autonomous, AI-Native Particle Accelerator

arXiv 2602.17536 ↗First posted 19 Feb 2026physics.acc-ph cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This position paper presents a vision for self-driving particle accelerators that operate autonomously with minimal human intervention. We propose that future facilities be designed through artificial intelligence (AI) co-design, where AI jointly optimizes the accelerator lattice, diagnostics, and science application from inception to maximize performance while enabling autonomous operation. Rather than retrofitting AI onto human-centric systems, we envision facilities designed from the ground up as AI-native platforms. We outline nine critical research thrusts spanning agentic control architectures, knowledge integration, adaptive learning, digital twins, health monitoring, safety frameworks, modular hardware design, multimodal data fusion, and cross-domain collaboration. This roadmap aims to guide the accelerator community toward a future where AI-driven design and operation deliver unprecedented science output and reliability.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 59 references that are in the map. First posted on arXiv 19 Feb 2026.

Builds on

15 of 59 references.

References · 15

  1. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  2. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  4. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  5. 2020Superconducting radio-frequency cavity fault classification using machine learning at Jefferson Laboratorycited by 15
  6. 2020Physics-Based Deep Neural Networks for Beam Dynamics in Charged Particle Acceleratorscited by 7
  7. 2020Autonomous Control of a Particle Accelerator using Deep Reinforcement Learningcited by 6
  8. 2024Cheetah: Bridging the Gap Between Machine Learning and Particle Accelerator Physics with High-Speed, Differentiable Simulationscited by 5
  9. 2025AI Safety Assurance for Automated Vehicles: A Survey on Research, Standardization, Regulationcited by 5
  10. 2025Osprey: Production-Ready Agentic AI for Safety-Critical Control Systemscited by 4
  11. 2023Rethinking Certification for Higher Trust and Ethical Safeguarding of Autonomous Systemscited by 2
  12. 2026Towards a Self-Driving Trigger at the LHC: Adaptive Response in Real Timecited by 2
3 more
  1. 2025Outlook Towards Deployable Continual Learning for Particle Acceleratorscited by 1
  2. 2025Efficient Dynamic and Momentum Aperture Optimization for Lattice Design Using Multipoint Bayesian Algorithm Executioncited by 1
  3. 2025From Natural Language to Control Signals: A Conceptual Framework for Semantic Channel Finding in Complex Experimental Infrastructurecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Agentic AI on Particle Accelerators
  2. 2025Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator
  3. 2026A3D: Agentic AI flow for autonomous Accelerator Design
  4. 2026GRACE: an Agentic AI for Particle Physics Experiment Design and Simulation
  5. 2026AI Agents Can Already Autonomously Perform Experimental High Energy Physics
  6. 2021Tackling Variabilities in Autonomous Driving
  7. 2026AI Agents, Language, Deep Learning and the Next Revolution in Science
  8. 2025PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research