发表机构
Tsinghua University; Texas Tech University（清华大学; 德克萨斯理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出人在回路、物理约束的多智能体工作流，用于自动构建并审计土塞演化模型，将平均最终隆起误差从58.4%降至9.0%，并发现隐藏实现问题，实现人类治理的工程求解器。
AI 中文摘要
工程预测要求将物理机制一致地转化为方程、离散化、代码和验证，然而尽管有局部检查，错误仍可能传播。人工智能（AI）智能体可自动化科学任务，但在物理约束和人类监督下协调并独立审计从理论到求解器的过程仍未解决。我们引入了一种人在回路、物理约束的多智能体工作流，其中人类专家定义可接受的物理和建模边界，而智能体检索证据、推导方程、实现求解器并审计理论到代码的链条。应用于吸力沉箱安装过程中的土塞演化，该工作流在物理知识和输入准备就绪后，通过2.9小时的智能体执行生成并审计了6种公式。在这些公式中，将渗流驱动的土体孔隙比演化添加到几何基线中，使14个剖面的平均绝对最终隆起误差从58.4%降至9.0%；所选模型进一步纳入了近壁膨胀，在9个最终状态案例中实现了12.4%的平均绝对百分比误差，在5个过程历史端点处实现了4.2%的误差。除了预测性能外，盲法重放恢复了所有9个目标问题，而独立审计在36项预定义检查通过后发现了5个实现问题。总体而言，这项工作将多智能体AI从任务自动化扩展到人类治理的工程求解器。
英文摘要
Engineering predictions require physical mechanisms to be translated consistently into equations, discretization, code, and validation, yet errors can propagate despite local checks. Artificial-intelligence (AI) agents automate scientific tasks, but coordinating and independently auditing the theory-to-solver process under physical constraints and human oversight remains unresolved. We introduce a human-in-the-loop, physics-constrained multi-agent workflow where human experts define admissible physics and modeling boundaries, while agents retrieve evidence, derive equations, implement solvers, and audit the theory-to-code chain. Applied to soil-plug evolution during suction-caisson installation, the workflow generated and audited 6 formulations in 2.9 h of agent execution once physical knowledge and inputs were prepared. Among these formulations, adding seepage-driven soil void-ratio evolution to the geometric baseline reduced mean absolute final-heave error from 58.4% to 9.0% across 14 profiles; the selected model further incorporated near-wall dilation and achieved mean absolute percentage errors of 12.4% across 9 final-state cases and 4.2% at the endpoints of 5 process histories. Beyond predictive performance, blinded replay recovered all 9 target problems, while an independent audit uncovered 5 implementation problems after 36 predefined checks had passed. Overall, this work extends multi-agent AI beyond task automation toward human-governed engineering solvers.
