EasyFoam:面向技能、证据驱动演化的 OpenFOAM 智能体
EasyFoam: Skill-Oriented OpenFOAM Agents with Evidence-Driven Evolution
Peng Yin · Zhiwei Chen · Tianyi Liu · Chen Li · Kai Li · Jian Cheng
中文摘要
大语言模型(LLM)智能体已能自动化 OpenFOAM 的端到端计算流体力学(CFD)工作流,但受两个关键限制:现有评测以教程级案例和执行导向指标为主,掩盖了可执行性与可接受性之间的差距,即仿真虽成功执行却常不满足数值或关注量(QoI)标准;领域知识又与特定智能体架构紧耦合,难以复用和持续改进。为此提出 ExtFoamBench,覆盖五个工作流变化维度,分别评估执行完成度、数值合理性与 QoI 满足度。同时提出 EasyFoam,将 CFD 专业知识解耦为模块化外部技能,由双环机制驱动:执行环依据显式任务需求构建工作流,并用结构化仿真证据诊断失败、指导定向修复;演化环将任务经验蒸馏为可复用技能更新,通过配对评估筛选。实验表明 EasyFoam 的任务接受率显著高于基线智能体。
关键要点
- 01现有评测偏重教程级案例与执行指标,掩盖了仿真可执行但不满足数值或 QoI 标准的差距
- 02ExtFoamBench 覆盖五个工作流变化维度,分别评估执行完成度、数值合理性与 QoI 满足度
- 03EasyFoam 将 CFD 专业知识解耦为模块化外部技能,由执行环与演化环双环机制驱动
- 04执行环用结构化仿真证据诊断失败并指导定向修复,演化环通过配对评估筛选技能更新
- 05EasyFoam 的任务接受率显著高于基线智能体,为自改进 CFD 智能体研究提供起点
解读
尚无解读。
原始英文摘要
arXiv:2611.14525v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly capable of automating end-to-end OpenFOAM workflows for computational fluid dynamics (CFD). However, current progress is bottlenecked by two critical limitations. First, existing evaluations are dominated by tutorial-level cases and execution-oriented metrics, masking a substantial executability--acceptability gap: successfully executed simulations often fail to satisfy prescribed numerical or quantity-of-interest (QoI) criteria. Second, domain expertise in existing systems is tightly coupled with bespoke agent architectures, limiting its reuse and continual refinement across agent implementations. To address these challenges, we introduce ExtFoamBench, a challenging benchmark for OpenFOAM agents that spans five axes of workflow variation, and separately assesses execution completion, numerical soundness, and QoI satisfaction. Complementing this, we propose EasyFoam, an agent framework that decouples CFD expertise into modular, externalized skills driven by a dual-loop mechanism. An execution loop constructs workflows from explicit task requirements and uses structured simulation evidence to diagnose failures and guide targeted repairs. Meanwhile, an evolution loop distills task experience into reusable skill updates selected through paired evaluation. Empirical evaluations demonstrate that EasyFoam achieves substantially higher task acceptance rates than baseline agents, establishing this work as a starting point for future research toward self-improving CFD agents.