Year: 2026
Type: preprint
Abstract: We present Experiment Automation Agents (EAA), a vision-language-model-driven agentic system designed to automate complex experimental microscopy workflows. EAA integrates multimodal reasoning, tool-augmented action, and optional long-term memory to support both autonomous procedures and interactive user-guided measurements. Built on a flexible task-manager architecture, the system enables workflows ranging from fully agent-driven automation to logic-defined routines that embed localized LLM queries. EAA further provides a modern tool ecosystem with two-way compatibility for Model Context Protocol (MCP), allowing instrument-control tools to be consumed or served across applications. We demonstrate EAA at an imaging beamline at the Advanced Photon Source, including automated zone plate focusing, natural language-described feature search, and interactive data acquisition. These results illustrate how vision-capable agents can enhance beamline efficiency, reduce operational burden, and lower the expertise barrier for users.
Source: arXiv (Cornell University)
Authors: Du, Ming, Luo, Yanqi, Banerjee, Srutarshi, Wojcik, Michael, Popovic, Jelena, Cherukara, Mathew J.
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: green
Funders: U.S. Department of Energy, University of Chicago, National Institutes of Health, Office of Science, National Institute of Allergy and Infectious Diseases, Basic Energy Sciences, Advanced Scientific Computing Research, Laboratory Directed Research and Development, Argonne National Laboratory
Awards: G102163711, G1055550527, G107546177, G1286251239, G1313983767, G1664757510, G2287611682, G262962599, G3075337988, G426311843, G498139845, G5387317844, G5607048534, G6848031779, G6918803902, G7583137537, G788322952, G878601127, Multi-Scale Evaluation and Mitigation of Toxicities Following Internal Radionuclide Contamination, G969889393, G993149817
OpenAlex ID: W7130454981
Cites:
Cited by:
Related to: