The development serves as the first step in the so-called self-driving labs of the future, where scientists let AI do the gruntwork as the human experts focus on the big questions.<\/p>\n
The project was funded by the U.S. Department of Energy (DOE) in collaboration with the Stanford Linear Accelerator Center (SLAC) National Accelerator Laboratory, a DOE research facility that houses equipment scientists use to study quantum matter, substances with features that can\u2019t be explained with classical physics.<\/p>\n
Studying quantum materials can be done by shooting X-rays through a tiny single crystal and watching how they scatter, as a way to make conclusions about their atomic structure and electron dynamics.<\/p>\n
Traditionally, X-ray scattering happens in a huge circular particle accelerator known as the synchrotron. The one at SLAC is called the Stanford Synchrotron Radiation Lightsource (SSRL) and is about 768 feet in circumference \u2014 on par with a city block in size. Inside that facility is a large pipe bent into a circular shape. Scientists inject electrons into the pipe and accelerate them until they\u2019re zooming around in circles, like runners on a giant racetrack.\u00a0<\/p>\n
Naturally, electrons want to move in a straight line. Powerful magnets bend their path, forcing them to race around in circles. Every time electrons change direction, they give off energy in the form of X-rays.<\/p>\n
Scientists channel the X-rays from the circular pipe into straight tunnels called beamlines, with each tunnel serving as a miniature lab. They perform experiments at multiple beamlines at the same time, pointing the X-rays at the crystal they\u2019re studying.<\/p>\n
In addition to SSRL, SLAC houses other light source facilities for studying materials and their properties. However, Bansil explained that many are oversubscribed \u2014 everyone wants to use them. Some only allow for one experiment at a time. As a result, the price tag climbs \u2014 quickly.\u00a0<\/p>\n
X-ray experiments also call for complex preparatory work. \u201cYou just can\u2019t walk in there and turn on a knob like you would in a kitchen,\u201d Bansil said.<\/p>\n
In addition to setting up the equipment, adjusting and repositioning the crystal sample burns up a hefty chunk of precious beam time, he explained, adding that you end up spending a good part of it \u201cjust taking your sample and aligning it so that it can be useful to get data.\u201d<\/p>\n
All in all, it\u2019s \u201ca real bottleneck,\u201d he said.<\/p>\n
Enter the AI scientist.<\/p>\n
While based on a large language (LLM) model similar to the type of AI technology behind ChatGPT, the AI scientist can physically interact with its environment by moving objects, collecting data and reading detector outputs \u2014 things out of reach for a typical chatbot.\u00a0\u00a0<\/p>\n
Bansil said that the choice of words \u2014 scientist as opposed to agent \u2014 was deliberate.\u00a0<\/p>\n
\u201cA generic AI agent will simply execute a prescribed set of instructions,\u201d he said. The AI scientist, on the other hand, reasons through the problem and adapts its approach based on observations \u2014 all without a handler micromanaging every step.<\/p>\n
![\"Arun](\"https:\/\/www.newsbeep.com\/nz\/wp-content\/uploads\/2026\/08\/neu_bz616r63w.jpg\")
Arun Bansil sees the AI scientist as a step toward self-driving laboratories that can run experiments with minimal human intervention. Photo by Matthew Modoono\/Northeastern University<\/p>\n
\u201cOne gives it a broad guidance to start with, and then it pretty much does its own thing,\u201d Bansil explained.<\/p>\n
The scientists put the AI scientist to the test in an actual SLAC X-ray facility by having it run through the steps of a simulated experiment.<\/p>\n
It passed with flying colors. <\/p>\n
The AI scientist sent commands to the diffractometer, analyzed the emerging pattern and made machinery adjustments when necessary. It figured out which tools to use for each step and pinned down the crystal\u2019s orientation in space with the utmost precision, Bansil said.<\/p>\n
The moment of truth came when the AI scientist faced an unexpected snag involving a motor involved in orienting the samples.\u00a0<\/p>\n
Avoiding a potential fiasco, it spotted the glitch and regrouped on the fly, Bansil said. Better yet, it learned from the experience, applying the knowledge in the steps that followed.<\/p>\n
The ability to change course secured the AI scientist\u2019s reputation as \u201ca real scientific collaborator capable of being a highly valuable partner in the effort,\u201d Bansil said.<\/p>\n
This project is part of a larger initiative at Northeastern University\u2019s Quantum Materials and Sensing Institute (QMSI) where Bansil serves as the founding director. QMSI, which specializes in developing quantum materials and devices, is working on creating \u201cthe self-driving laboratories of tomorrow,\u201d he said, and the AI Scientist marks the first step in making that vision a reality.<\/p>\n
Self-driving labs are not new. For example, Boston\u2019s Atinary Technologies<\/a>, a self-driving chemistry lab located in Boston\u2019s Seaport, crunches out an amount of weekly physical chemistry experimental data that\u2019s on par with what a typical Ph.D. student produces over the course of their degree, according to Lo\u00efc Roch, one of the lab\u2019s co-founders.<\/p>\n