AI Copilot Retains Berkeley’s X-Ray Particle Accelerator on Observe

Within the rolling hills of Berkeley, California, an AI agent is supporting high-stakes physics experiments on the Superior Mild Supply (ALS) particle accelerator.

Researchers on the Lawrence Berkeley Nationwide Laboratory ALS facility lately deployed the Accelerator Assistant, a big language mannequin (LLM)-driven system to maintain X-ray analysis on observe.

The Accelerator Assistant — powered by an NVIDIA H100 GPU harnessing CUDA for accelerated inference — faucets into institutional data information from the ALS assist workforce and routes requests by way of Gemini, Claude or ChatGPT. It writes Python and solves issues, both autonomously or with a human within the loop.

That is no small job. The ALS particle accelerator sends electrons touring close to the pace of sunshine in a 200-yard round path, emitting ultraviolet and X-ray gentle, which is directed by way of 40 beamlines for 1,700 scientific experiments per yr. Scientists worldwide use this course of to review supplies science, biology, chemistry, physics and environmental science.

On the ALS, beam interruptions can final minutes, hours or days, relying on the complexity, halting concurrent scientific experiments in course of. And far can go fallacious: the ALS management system has greater than 230,000 course of variables.

“It’s actually necessary for such a machine to be up, and after we go down, there are 40 beamlines that do X-ray experiments, and they’re ready,” mentioned Thorsten Hellert, employees scientist from the Accelerator Expertise and Utilized Physics Division at Berkeley Lab and lead creator of a analysis paper on the groundbreaking work.

Till now, facility employees troubleshooting points have needed to shortly determine the areas, retrieve information and collect the proper personnel for evaluation below intense time stress to get the system again up and working.

“The novel method presents a blueprint for securely and transparently making use of giant language model-driven techniques to particle accelerators, nuclear and fusion reactor services, and different complicated scientific infrastructures,” mentioned Hellert.

The analysis workforce demonstrated that the Accelerator Assistant can autonomously put together and run a multistage physics experiment, slicing setup time and decreasing efforts by 100x.

Making use of Context Engineering Prompts to Accelerator Assistant

The ALS operators work together with the system by way of both a command line interface or Open WebUI, which permits interplay with numerous LLMs and is accessible from management room stations, in addition to remotely. Beneath the hood, the system makes use of Osprey, a framework developed at Berkeley Lab to use agent-based AI safely in complicated management techniques.

Every consumer is authenticated and the framework maintains personalised context and reminiscence throughout periods, and a number of periods could be managed concurrently. This permits customers to arrange distinct duties or experiments into separate threads. These inputs are routed by way of the Accelerator Assistant, which makes connections to the database of greater than 230,000 course of variables, a historic database archive service and Jupyter Pocket book-based execution environments.

“We attempt to engineer the context of each language mannequin name with no matter prior data we’ve from this execution up so far,” mentioned Hellert.

Inference is finished both domestically — utilizing Ollama, which is an open-source software for working LLMs with a private pc, on an H100 GPU node situated throughout the management room community — or externally with the CBorg gateway, which is a lab-managed interface that routes requests to exterior instruments resembling ChatGPT, Claude or Gemini.

The hybrid structure balances safe, low-latency, on-premises inference with entry to the most recent basis fashions. Integration with EPICS (Experimental Physics and Industrial Management System) permits operator-standard security constraints for direct interplay with accelerator {hardware}. EPICS is a distributed management system utilized in large-scale scientific services resembling particle accelerators. Engineers can write Python code in Jupyter Pocket book that may talk with it.

Mainly, conversational enter is become a transparent pure language job description for goals with out redundancy. Exterior data resembling personalised reminiscence tied to customers, documentation and accelerator databases are built-in to help with terminology and context.

“It’s a big facility with a whole lot of specialised experience,” mentioned Hellert. “A lot of that data is scattered throughout groups, so even discovering one thing easy — just like the tackle of a temperature sensor in a single a part of the machine — can take time.”

Tapping Accelerator Assistant to Support Engineers, Fusion Vitality Improvement

Utilizing the Accelerator Assistant, engineers can begin with a easy immediate describing their purpose. Behind the scenes, the system attracts on rigorously ready examples and key phrases from accelerator operations to information the LLM’s reasoning.

“Every immediate is engineered with related context from our facility, so the mannequin already is aware of what sort of job it’s coping with,” mentioned Hellert.

Every agent is an skilled in that area, he mentioned.

As soon as the duty is outlined, the agent brings collectively its specialised capabilities — resembling discovering course of variables or navigating the management system — and might robotically generate and run Python scripts to investigate information, visualize outcomes or work together safely with the accelerator itself.

“That is one thing that may prevent critical time — within the paper, we are saying two orders of magnitude for such a immediate,” mentioned Hellert.

Wanting forward, Hellert goals to have the ALS engineers put collectively a wiki that paperwork the numerous processes that go on to assist the experiments. These paperwork might assist the brokers run the services autonomously — with a human within the loop to approve the plan of action.

“On these high-stakes scientific experiments, even when it’s only a TEM microscope or one thing that may value $1 million, a human within the loop could be essential,” mentioned Hellert.

The work has already expanded past ALS as a part of the DOE’s Genesys mission, with the framework being deployed throughout U.S. particle accelerator services. Subsequent up, Hellert simply started collaborating with engineers on the ITER fusion reactor — the world’s largest — in France for implementing the framework to be used within the fusion reactor facility. He additionally has a collaboration within the works with the Extraordinarily Massive Telescope ELT, in northern Chile.

Benefiting Humanity: Scientific Influence of Experiments Supported by ALS

Past optimizing the accelerator and different industrial operations, the work on the ALS straight permits scientific breakthroughs with world affect. The power’s secure X-ray beams underpin analysis in well being, local weather resilience and planetary science.

Through the COVID-19 pandemic, ALS researchers helped characterize a uncommon antibody that might neutralize SARS-CoV-2. Structural biology experiments at Beamline 4.2.2 revealed how six molecular loops of the antibody latch onto and disable the viral spike protein. The findings supported the speedy growth of a therapeutic that remained efficient by way of a number of variants.

ALS science additionally contributes to climate-focused analysis. Metallic-organic frameworks (MOFs) — a category of porous supplies able to capturing water or carbon dioxide from air — had been extensively studied throughout a number of ALS beamlines. These experiments supported foundational work that finally led to the 2025 Nobel Prize in Chemistry, recognizing the transformative potential of MOFs for sustainable water harvesting and carbon administration.

In planetary science, ALS measurements of samples returned from NASA’s OSIRIS-REx mission helped hint the chemical historical past of asteroid Bennu. X-ray analyses supplied proof that such asteroids carried water and molecular precursors of life to early Earth, deepening our understanding of the origins of the planet’s liveable circumstances.