AI agents for photonic integrated circuit design automation
Name
046113_1_5.0300741.pdf
Description
Published version
Size
6.38 MB
Format
Adobe PDF
Checksum (MD5)
63c2559548b97b247c78f2f3a2e4946b
Author(s)
Sharma, Ankita
Fu, Yuqi
Ansari, Vahid
Iyer, Rishabh
Kuang, Fiona
Mistry, Kashish
Aishy, Raisa Islam
Ahmad, Sara
Matres, Joaquin
Englund, Dirk R
Date Issued
December 30, 2025
Journal
APL Machine Learning
Publisher
AIP Publishing
Citation
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; AI agents for photonic integrated circuit design automation. APL Mach. Learn. 1 December 2025; 3 (4): 046113.
Version
Final published version
Abstract
We present photonics intelligent design and optimization, a proof-of-concept multi-agent framework that converts natural-language photonic integrated circuit (PIC) design requests into layout mask files. This work demonstrates end-to-end PIC design automation using large language models (LLMs), with the goal of achieving structurally valid rather than performance-qualified layouts. We compare seven reasoning LLMs 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 ≤15 components, o1, Gemini-2.5-pro, and Claude Opus 4 achieved the highest end-to-end pass@5 success rates of ∼57%, with Gemini-2.5-pro requiring the fewest output tokens and the lowest cost. Future work will extend this framework toward performance qualification through expanded datasets, tighter simulation and optimization loops, and fabrication feedback integration.
MIT Department
Massachusetts Institute of Technology. Research Laboratory of Electronics
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1063/5.0300741
