AI Agents for Photonic Integrated Circuit Design Automation
This work addresses the problem of automating complex photonic integrated circuit design for engineers and researchers, representing an incremental advancement by applying existing reasoning LLMs to a new domain-specific task.
The researchers tackled the problem of automating photonic integrated circuit design by developing PhIDO, a multi-agent framework that converts natural-language requests into layout mask files, achieving up to 91% success rate for single-device designs and approximately 57% pass@5 success rates for designs with ≤15 components using models like o1, Gemini-2.5-pro, and Claude Opus 4.
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.