NeuDiff Agent: A Governed AI Workflow for Single-Crystal Neutron Crystallography
Zhongcan Xiao (1), Leyi Zhang (1, 2), Guannan Zhang (3), Xiaoping Wang (1) ((1) Neutron Scattering Division, Oak Ridge National Laboratory, Oak Ridge, Tennesse USA, (2) Department of Linguistics, University of Illinois Urbana-Champaign, Urbana, Illinois, USA

TL;DR
NeuDiff Agent is an AI-driven workflow that automates the complex process of neutron crystallography analysis, significantly reducing analysis time while ensuring validated, publication-ready results with full traceability.
Contribution
It introduces a governed AI workflow for neutron crystallography that automates data reduction, analysis, and validation with strict governance and provenance tracking.
Findings
Reduces analysis time from 435 to around 90 minutes
Produces validated crystal structures with no critical alerts
Maintains full traceability and auditability of the workflow
Abstract
Large-scale facilities increasingly face analysis and reporting latency as the limiting step in scientific throughput, particularly for structurally and magnetically complex samples that require iterative reduction, integration, refinement, and validation. To improve time-to-result and analysis efficiency, NeuDiff Agent is introduced as a governed, tool-using AI workflow for TOPAZ at the Spallation Neutron Source that takes instrument data products through reduction, integration, refinement, and validation to a validated crystal structure and a publication-ready CIF. NeuDiff Agent executes this established pipeline under explicit governance by restricting actions to allowlisted tools, enforcing fail-closed verification gates at key workflow boundaries, and capturing complete provenance for inspection, auditing, and controlled replay. Performance is assessed using a fixed prompt protocol…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning in Materials Science · Nuclear Physics and Applications · Enzyme Structure and Function
