cs.AINov 6, 2026

Auditable Human-Agent Teams for Autonomous X-ray Experimentation

Authors: Gunik Luthra, Ronald J. Pandolfi, Benjamin T. Diroll, Ricky Ronquillo, Ruipeng Li, Christopher B. Murray, Marcus M. Noack, Kevin G. Yager, 

Organizations: Center for Functional Nanomaterials, Brookhaven National Laboratory, Upton, NY 11973, USA · Applied Mathematics and Computational Research, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA · Center for Nanoscale Materials, Argonne National Laboratory, Lemont, IL 60439, USA · University of Pennsylvania, Philadelphia, PA 19104, USA · 

Abstract

Closed-loop autonomous experimentation can accelerate scientific discovery, but implementation effort limits accessibility. Agentic systems may lower this barrier, although sustained operation on physical instruments remains largely unexplored. Here, using coding-agent infrastructure grounded in validated scientific methods, we demonstrate autonomous synchrotron X-ray experiments on nanoparticle superlattices under evolving, human-defined objectives. Complete human-agent and agent-agent transcripts enable an audit that reconstructs decision provenance and characterizes the division of cognitive labor. Across three experiments, 61-67% of messages involved interpretation or judgment, while the share of methodological and scientific contributions increased from 46% in the setup-focused first experiment to 56-61% in later experiments. Provenance showed that 59-68% of error corrections involved multiple participants and that about half of all decisions incorporated the input of another participant. These results may guide design principles for multi-agent scientific systems and inform future agent harnesses, model training, and accessible autonomous experimentation.

Figures & tables

Explore similar work

CardsList
  1. Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator

    Sep 21, 2025Thorsten Hellert, Drew Bertwistle, Simon C. Leemann +2AI for ScienceAgentic Workflows

  2. DiscoveryAgent: A Framework for Scientist-centric Agentic AI

    Nov 16, 2026Owen Queen, Ioana Ciuca, Emma Dann +9AI-Assisted Scientific ResearchAutonomous Research Agents