NeuDiff Agent:单晶中子晶体学的受控AI工作流
NeuDiff Agent: A Governed AI Workflow for Single-Crystal Neutron Crystallography
AI总结:
NeuDiff Agent通过受控AI工作流提升单晶中子晶体学的分析效率和结果准确性,实现快速生成验证的晶体结构和出版级CIF。
摘要:
大规模设施日益面临分析和报告延迟成为科学通量的限制步骤的问题,特别是对于结构和磁性复杂样品,这些样品需要迭代的减少、整合、细化和验证。为提高结果时间和分析效率,NeuDiff Agent被引入作为TOPAZ在Spallation Neutron Source上的受控工具使用AI工作流,将仪器数据产品通过减少、整合、细化和验证,最终得到一个验证的晶体结构和出版级CIF。NeuDiff Agent在明确的治理下执行此已建立的流程,通过限制操作到允许的工具,强制在关键工作流边界处执行fail-closed验证门,并捕获完整的可追溯性以供检查、审计和受控重放。通过固定提示协议和重复的端到端运行,使用两个大型语言模型后端进行性能评估,用户和机器时间被分割,并量化了干预负担和恢复行为。在参考案例基准测试中,NeuDiff Agent将运行时间从435分钟(手动)减少到86.5(4.7)到94.4(3.5)分钟(4.6-5.0倍更快),同时生成一个没有checkCIF级别A或B警报的验证CIF。这些结果确立了在设施晶体学中部署代理AI的可行路线,同时保持可追溯性和面向出版的验证要求。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。