AI

AI-Guided Autonomous Experiments Link Up With Remote Supercomputers

AI TIMES ·

AI-Guided Autonomous Experiments Link Up With Remote Supercomputers
The research team, along with the National Science Data Fabric (NSDF), the Cornell High Energy Synchrotron Source (CHESS), Oak Ridge National Laboratory (ORNL), the National Institute of Standards and Technology (NIST), and industry partner ViSOAR LLC, won an HPCwire Award in recognition of their achievement in advancing autonomous experiment technology from a system limited to a single research facility into a distributed system connecting research infrastructure across the United States. [Photo: Cornell University]

✦ AI Summary

According to AI TIMES, Cornell University researchers have built an autonomous experimentation infrastructure in which AI analyzes experimen…

According to AI TIMES, Cornell University researchers have built an autonomous experimentation infrastructure in which AI analyzes experimental data, then decides the next measurement location on its own and links in real time with remote computing resources. Cornell University said on November 18 that the achievement won the 2026 HPCwire Editors’ Choice Award. At the core of the system is the automation of a closed-loop process in which researchers used to review results and reconfigure equipment each time. The setup measures stress inside metal using high-energy X-rays, after which AI selects the spots where more information is needed and directs follow-up measurements, with the equipment and remote resources repeating that process. Another key feature is that it ties together equipment control, active learning, and data transfer technologies from multiple institutions into a single workflow, extending automation that had been confined to individual facilities into a distributed research environment. The researchers also indicated the possibility of expanding the system to other materials and biology research, while also considering a future in which researchers bring their own AI models and connect them to the platform.

Perspective

The significance of this issue lies in the fact that AI has moved beyond a tool that merely helps interpret research data and has instead risen to an operational layer that determines the actual order of experiments. In particular, if automation becomes possible even when equipment and computing resources are not in one place, research capacity may be shaped more by connectivity and workflow design than by the equipment a given facility owns. In the end, research sites could see a larger shift toward a competitive edge defined by how quickly they combine resources and repeat experiments, as much as by analytical accuracy.

This perspective is BizCrush's own commentary and is not part of the reporting by AI TIMES.

This article was produced with the help of an automated content generation algorithm.


Source: AI TIMES

View original

This article was summarized and organized by BizCrush based on the original article from AI TIMES. For exact quotations and full details, please refer to the original article.

BizCrush Inc. · CEO Taemin Kwak

HQ 100 Middlefield Rd, Menlo Park, CA 94025, USA

Korea office Z112, Room 602, 6F, 602 Yeongdong-daero, Gangnam-gu, Seoul, Republic of Korea

Support help@bizcrush.ai · Partnerships business@bizcrush.ai

AI Notice

Some features use generative AI.

Those features carry their own pre-use notice and mark AI-generated results. AI output is for reference only — always check the original source and consult an expert before making an important decision.