LLM编排代理用于定向耦合器设计 带自洽本征模与FDTD验证

An LLM-Orchestrated Agent for Directional-Coupler Design with Self-Consistent Eigenmode and FDTD Validation

精选理由

这篇论文让LLM指挥本征模和FDTD模拟自动设计定向耦合器,误差仅0.0017,省去手动调参的麻烦。

AI 摘要

论文提出一个由大语言模型(LLM)编排的设计代理,用于硅绝缘体(SOI)2×2定向耦合器。LLM提出候选间隙值并判断收敛,频率域本征模求解器估算耦合系数κ,独立时域有限差分(FDTD)进行验证。两个求解器均基于相同的2D有效折射率模型,设计κ与FDTD响应之间残差对应一个固定额外耦合长度2.837 μm。该代理实现50/50分束器,FDTD测得的交叉分数为0.498(目标0.500),残差0.0017。结果在2D有效折射率模型内自洽,LLM经过多次尝试成功交付设计。

原文 · arXiv cs.AI

An LLM-Orchestrated Agent for Directional-Coupler Design with Self-Consistent Eigenmode and FDTD Validation

We present a design agent which is a Large Language Model (LLM) that orchestrates, but does not perform, the numerical simulations to design a silicon-on-insulator (SOI) $2\times2$ directional coupler. We choose a symmetric phase-matched coupler where a lot of analytical results are available that help the design strategy. The LLM proposes candidate gap values (a geometrical dimension size) and judges convergence, while all physics is owned by deterministic solvers: a frequency-domain eigenmode solver estimates the coupling coefficient~$κ$ for the current design, and an independent Finite-Difference Time-Domain (FDTD) stage validates it. Both solvers operate on a common slab-projected two-dimensional (2D) effective-index reduction of the silicon film, so the design~$κ$ and the FDTD response are consistent by problem design; the residual between them is shown to be a single constant phase offset~$φ$, attributable to a fixed excess coupling length $L_{\mathrm{extra}}=\SI{2.837(11)}{\micro\meter}$ that we find invariant across a factor-of-two range in~$κ$. Folding this offset into a closed-loop length correction, the agent delivers a $50/50$ splitter whose FDTD-measured cross fraction is $0.498$ (target $0.500$), a residual of $0.0017$. Results are made self-consistent within the 2D effective-index model; and the LLM succeeds in delivering a suitable design over a number of attempts.

LLM编排代理用于定向耦合器设计 带自洽本征模与FDTD验证 · AI 热点