NeuDiff Agent: A Governed AI Workflow for Single-Crystal Neutron Crystallography
This addresses analysis bottlenecks for large-scale neutron facilities, offering an incremental improvement by automating an established pipeline with governance for traceability.
The paper tackles the problem of analysis latency in neutron crystallography by introducing NeuDiff Agent, a governed AI workflow that automates data processing from instrument data to validated crystal structures, reducing wall time from 435 minutes manually to 86.5-94.4 minutes (4.6-5.0x faster) with no critical validation alerts.
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 route to deploy agentic AI in facility crystallography while preserving traceability and publication-facing validation requirements.