NeuDiff Agent: A Governed AI Workflow for Single-Crystal Neutron Crystallography
cs.AI
Submitted: 2026-02-18
Updated: 2026-02-18
Journal ref: J. Appl. Cryst. 59 (2026) 1102-1111
DOI: 10.1107/S1600576726004474
License: http://creativecommons.org/licenses/by/4.0/
The gist: Large-scale facilities increasingly face analysis and reporting latency as the limiting step in scientific throughput…
Terminology
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 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.
Sources
- Improving quantum-transition temperatures in BaFe2As2-based crystals by removing local-lattice strain & electronic-structure disorder
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- Large Language Models: A Survey
- Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents