人类主导、物理约束的多智能体工作流，2.9 小时构建可审计的土塞演化模型
Human-guided physics-constrained AI agents construct an auditable model of soil-plug evolution
工程师定规矩，AI 智能体 2.9 小时写出 6 套土塞演化求解器，隆起误差从 58.4% 降到 9.0%。
一篇 arXiv 论文提出人在环路、物理约束的多智能体工作流：人类专家划定可用物理假设与建模边界，智能体负责检索证据、推导方程、实现求解器并审计从理论到代码的全链条。
在吸力沉箱安装的土塞演化问题上，工作流在 2.9 小时智能体执行时间内生成并审计了 6 套公式体系。
其中在几何基线上加入渗流驱动的孔隙比演化后，14 个剖面的最终隆起平均绝对误差从 58.4% 降至 9.
0%；最终选定的模型再加入近壁剪胀，在 9 个最终状态案例上的平均绝对百分比误差为 12.
4%，在 5 条过程历史的端点处为 4.2%。
独立审计在 36 项预定义检查全部通过后仍发现 5 处实现问题，盲测重放则复现了全部 9 个目标问题。
Human-guided physics-constrained AI agents construct an auditable model of soil-plug evolution
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.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include agents, AI for Science, physics constraints.
Source attribution: curated from arXiv cs.AI (@Jie Shi, Yimin Lu, Zhongkun Ouyang).
