发表机构
Kitware, Inc.（Kitware公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种基于领域本体和模型上下文协议（MCP）的架构，将LLM的意图解释、确定性领域工具执行与LLM解释分离，在ParaView服务器上实现了CFD后处理和拓扑数据分析，提升了结果解释准确率，减少了脚本生成类故障。
AI 中文摘要
科学分析工作流通过紧密耦合的操作序列编码了深厚的领域知识，其正确性取决于工具选择、执行顺序和参数设置。研究流动分离的计算流体力学（CFD）工程师必须提取壁面切应力、识别皮肤摩擦中的过零点，并通过边界层剖面进行确认：这一链条既需要领域专业知识，也需要可视化工具的熟练运用。当前LLM辅助的科学可视化方法生成的代码将这类知识隐式编码，且常常出错，生成的代码可执行但结果错误。本文提出一种架构，通过模型上下文协议（MCP）连接意图解释（LLM）、执行（确定性领域工具）和解释（LLM）三部分，并以领域本体为基础，将规划约束为有效的分析链条。我们在同一ParaView服务器基础设施上的两个领域实例化该架构：计算流体力学后处理和通过拓扑工具包（TTK）进行的拓扑数据分析。添加第二个领域仅需一个本体和现有过滤器的工具包装器，无需修改架构、协议或部署。该设计从结构上消除了影响脚本生成的整类故障（如API幻觉和缺失的管道阶段），并减少了剩余的策略性错误。跨两个领域的 ablation 研究确定了本体的经验效果：它不会改变规划器选择的工具（这部分已可靠），而是纠正模型解释结果的方式，将解释准确率从0.41提升至0.91，且仅当相关事实以限定形式而非批量形式检索时才生效。ParaView的客户端-服务器模型通过轻量级浏览器客户端将分析能力扩展到生产级数据集。
英文摘要
Scientific analysis workflows encode deep domain knowledge through sequences of tightly coupled operations where correctness depends on tool selection, execution order, and parameterization. A CFD engineer investigating flow separation must extract wall shear stress, identify zero-crossings in skin friction, and confirm with boundary-layer profiles: a chain that requires both domain expertise and proficiency with visualization tools. Current approaches to LLM-assisted scientific visualization generate scripts that encode this knowledge implicitly, and often incorrectly, producing code that executes but yields wrong results. We present an architecture that separates intent interpretation (LLM) from execution (deterministic domain tools) from explanation (LLM), connected by the Model Context Protocol (MCP) and grounded by domain ontologies that constrain planning to valid analysis chains. We instantiate the architecture in two domains on the same ParaView server infrastructure: computational fluid dynamics post-processing and topological data analysis via the Topology ToolKit (TTK). Adding the second domain required only an ontology and tool wrappers around existing filters, with no change to the architecture, protocol, or deployment. By construction the design removes whole classes of failure that affect script generation (such as API hallucination and missing pipeline stages) and narrows the strategic errors that remain. An ablation across both domains locates the ontology's empirical effect: it does not change which tools the planner selects, which is already reliable, but corrects how the model interprets results, raising interpretation accuracy from 0.41 to 0.91, and only when the relevant fact is retrieved in scoped rather than bulk form. ParaView's client-server model carries analysis to production-scale datasets through a thin browser client.
Comments27 pages, 12 figures
