{"ID":2881274,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.14123","arxiv_id":"2508.14123","title":"AI Agents for Photonic Integrated Circuit Design Automation","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.","short_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 d...","url_abs":"https://arxiv.org/abs/2508.14123","url_pdf":"https://arxiv.org/pdf/2508.14123v1","authors":"[\"Ankita Sharma\",\"YuQi Fu\",\"Vahid Ansari\",\"Rishabh Iyer\",\"Fiona Kuang\",\"Kashish Mistry\",\"Raisa Islam Aishy\",\"Sara Ahmad\",\"Joaquin Matres\",\"Dirk R. Englund\",\"Joyce K. S. Poon\"]","published":"2025-08-18T18:20:32Z","proceeding":"cs.AR","tasks":"[\"cs.AR\",\"cs.AI\",\"physics.app-ph\",\"physics.optics\"]","methods":"[\"Language Model\"]","has_code":false}