The deployment of autonomous agents for Computational Fluid Dynamics (CFD), is critically limited by the probabilistic nature of Large Language Models (LLMs), which struggle to enforce the strict conservation laws and numerical stability required for physics-based simulations. Reliance on purely semantic Retrieval Augmented Generation (RAG) often leads to "context poisoning," where agents generate linguistically plausible but physically invalid configurations due to a fundamental Semantic-Physical Disconnect. To bridge this gap, this work introduces PhyNiKCE (Physical and Numerical Knowledgeable Context Engineering), a neurosymbolic agentic framework for trustworthy engineering. Unlike standard black-box agents, PhyNiKCE decouples neural planning from symbolic validation. It employs a Symbolic Knowledge Engine that treats simulation setup as a Constraint Satisfaction Problem, rigidly enforcing physical constraints via a Deterministic RAG Engine with specialized retrieval strategies for solvers, turbulence models, and boundary conditions. Validated through rigorous OpenFOAM experiments on practical, non-tutorial CFD tasks using Gemini-2.5-Pro/Flash, PhyNiKCE demonstrates a 96% relative improvement over state-of-the-art baselines. Furthermore, by replacing trial-and-error with knowledge-driven initialization, the framework reduced autonomous self-correction loops by 59% while simultaneously lowering LLM token consumption by 17%. These results demonstrate that decoupling neural generation from symbolic constraint enforcement significantly enhances robustness and efficiency. While validated on CFD, this architecture offers a scalable, auditable paradigm for Trustworthy Artificial Intelligence in broader industrial automation.

翻译：在计算流体动力学（CFD）中部署自主智能体，受到大语言模型（LLM）概率性本质的严重限制，这些模型难以强制执行基于物理模拟所必需的严格守恒定律和数值稳定性。对纯语义检索增强生成（RAG）的依赖常常导致“上下文污染”，由于根本的语义-物理脱节，智能体会生成语言上合理但物理上无效的配置。为了弥合这一差距，本文提出了PhyNiKCE（物理与数值知识化上下文工程），一种用于可信工程设计的神经符号智能体框架。与标准的黑盒智能体不同，PhyNiKCE将神经规划与符号验证解耦。它采用一个符号知识引擎，将模拟设置视为一个约束满足问题，通过一个确定性RAG引擎并辅以针对求解器、湍流模型和边界条件的专门检索策略，来严格强制执行物理约束。通过在实用、非教程性质的CFD任务上使用Gemini-2.5-Pro/Flash进行严格的OpenFOAM实验验证，PhyNiKCE相较于最先进的基线方法显示出96%的相对性能提升。此外，通过用知识驱动的初始化取代试错过程，该框架将自主自校正循环减少了59%，同时将LLM令牌消耗降低了17%。这些结果表明，将神经生成与符号约束强制执行解耦，能显著增强鲁棒性和效率。虽然已在CFD领域得到验证，但该架构为更广泛的工业自动化领域提供了一个可扩展、可审计的可信人工智能范式。