AI Agents for Photonic Integrated Circuit Design Automation

Ankita Sharma, YuQi Fu, Vahid Ansari, Rishabh Iyer, Fiona Kuang +6 more
8/18/2025
cs.ARcs.AIphysics.app-ph

No confident code implementation found for this paper.

Abstract

We present Photonics Intelligent Design and Optimization (PhIDO), a multi-agent framework that converts natural-language photonic integrated circuit (PIC) design requests into layout mask files. We compare 7 reasoning large language models for PhIDO using a testbench of 102 design descriptions that ranged from single devices to 112-component PICs. The success rate for single-device designs was up to 91%. For design queries with less than or equal to 15 components, o1, Gemini-2.5-pro, and Claude Opus 4 achieved the highest end-to-end pass@5 success rates of approximately 57%, with Gemini-2.5-pro requiring the fewest output tokens and lowest cost. The next steps toward autonomous PIC development include standardized knowledge representations, expanded datasets, extended verification, and robotic automation.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

MAPS: Multi-Fidelity AI-Augmented Photonic Simulation and Inverse Design Infrastructure

84% match2025

DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent

82% match2024

An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design

82% match2025

Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents

80% match2026

Toward Lifelong-Sustainable Electronic-Photonic AI Systems via Extreme Efficiency, Reconfigurability, and Robustness

80% match2025

ChipXplore: Natural Language Exploration of Hardware Designs and Libraries

79% match2024

Cite this paper

@article{sharma2025agents,
  title  = {AI Agents for Photonic Integrated Circuit Design Automation},
  author = {Ankita Sharma and YuQi Fu and Vahid Ansari and Rishabh Iyer and Fiona Kuang and Kashish Mistry and Raisa Islam Aishy and Sara Ahmad and Joaquin Matres and Dirk R. Englund and Joyce K. S. Poon},
  year   = {2025},
  eprint = {2508.14123},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.14123v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.14123.svg)](https://codeofpaper.com/paper/2508.14123)

Discussion