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

arXiv: https://arxiv.org/abs/2606.22493 · HTML: https://mlsanity.com/paper/2606.22493/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 4 of 4)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [A Survey of Research in Large Language Models for Electronic Design Automation](https://mlsanity.com/paper/2501.09655/) (2025)
- [Toward Automated Simulation Research Workflow through LLM Prompt Engineering Design](https://mlsanity.com/paper/2408.15512/) (2024)

## Abstract (arXiv)

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) 2×2 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~kappa 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~kappa 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 Lextra=SI2.837(11)micrometer that we find invariant across a factor-of-two range in~kappa. 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.