• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:NeuDiff Agent: A Governed AI Workflow for Single-Crystal Neutron Crystallography View PDFAbstract: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 and repeated end-to-end runs with two large language model backends, with user and machine time partitioned and intervention burden and recovery behaviors quantified under gating. • In a reference-case benchmark, NeuDiff Agent reduces wall time from 435 minutes (manual) to 86.5(4.7) to 94.4(3.5) minutes (4.6-5.0x faster) while producing a validated CIF with no checkCIF level A or B alerts. • These results establish a practical
Article Summaries:
- NeuDiff Agent is a governed artificial‑intelligence workflow designed for the TOPAZ instrument at the Spallation Neutron Source. It automates the full reduction, integration, refinement, and validation pipeline for single‑crystal neutron diffraction data, producing a publication‑ready CIF while enforcing strict governance: only allowlisted tools are used, fail‑closed verification gates are applied at key stages, and complete provenance is recorded for auditability. In benchmark tests, the agent cuts wall time from 435 minutes (manual) to about 86-94 minutes- a 4.6‑ to 5.0‑fold speed‑up-without generating any checkCIF level A or B alerts. The study demonstrates that agentic AI can be deployed in high‑throughput crystallography while preserving traceability and validation standards.
Sources: