作为物理系统模型供应商的大语言模型智能体:Modelica中的校准与接受
LLM Agents as Suppliers of Physical System Models: Calibration and Acceptance in Modelica
AI总结:
本文让LLM编码智能体作为供应商构建Modelica模型,探究模型接受标准,发现需依据模型集合判定,明确阈值可提升交付通过率,结论适用于模型规定不足的场景。
摘要:
为获取设备模型,客户向供应商提供描述(有时附带记录数据或目标响应),并依据该交付内容接受模型。本文让大语言模型(LLM)编码智能体作为供应商,在附带数据的交付任务中,基于库组件为四个模拟系统及一个真实开关磁体构建Modelica模型,并探究“接受”的含义。多个智能体的建模结果达到噪声下限,但一次交付会对应一组模型:描述未明确部分结构,数据仅能将结构限定至约定精度。因此,本文依据模型是否属于该集合而非是否匹配单一参考来判定接受,且在行为之上增加了物理不变量层面的要求:某模型虽达到噪声下限,却因违反物理不变量(属于造能模型)而被排除。可解释性成为交付模型的属性,需在变体上测试、在无模型处读取,并通过交付过程塑造。多数失败案例是拟合模型在自身拟合数据上存在系统性残差,原因是交付未明确“足够接近”的标准。后续研究中,明确阈值后智能体会与之对比,更多交付得以通过。该结论适用于所有交付对模型的规定不足的场景,这类模型旨在被读取而非仅运行。
英文摘要:
To procure a model of a device, a client hands a supplier a description, sometimes with recorded data or a target response, and accepts the model against this handover. We let LLM coding agents act as the supplier on handovers with data, building Modelica models from library components for four simulated systems and a real switching magnet, and ask what acceptance certifies. Several agents reach the noise floor, but a handover admits a set of models: the description leaves parts of the structure open, and the data narrow it only to the agreed accuracy. We therefore accept by membership in this set, not by matching one reference, and add layers above behaviour: a physical invariant exposes an energy-creating model at the noise floor. Interpretability becomes a property of the delivered model, tested on a variant, read where none exists and shaped through the handover. Most failures are fits delivered with a systematic residual on their own fitting data, where the handover left open how close is close enough. In a follow-up, stating a threshold makes the agents compare against it, and more deliveries pass. The argument applies wherever a handover underspecifies a model meant to be read, not only run.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。