EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI agents for photonic integrated circuit design automation

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

APL Machine Learning · 01.12.2025 · 3 (4)

DOI: 10.1063/5.0300741 ↗

Kurz gefasst

Fachartikel in der Zeitschrift APL Machine Learning, online erschienen am 30.12.2025. Verfasst von Ankita Sharma und 10 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, Max-Planck-Gesellschaft.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Natural Sciences and Engineering Research Council of Canada
  • Max-Planck-Gesellschaft

Zitieren

APA

Sharma, A., Fu, Y., Ansari, V., Iyer, R., Kuang, F., Mistry, K., Aishy, R. I., Ahmad, S., Matres, J., Englund, D. R., & Poon, J. K. S. (2025). AI agents for photonic integrated circuit design automation. APL Machine Learning, 3(4). https://doi.org/10.1063/5.0300741

Vancouver

Sharma A, Fu Y, Ansari V, Iyer R, Kuang F, Mistry K, et al. AI agents for photonic integrated circuit design automation. APL Machine Learning. 2025;3(4). doi:10.1063/5.0300741

BibTeX
@article{Sharma2025,
  author = {Sharma, Ankita and Fu, Yuqi and Ansari, Vahid and Iyer, Rishabh and Kuang, Fiona and Mistry, Kashish and Aishy, Raisa Islam and Ahmad, Sara and Matres, Joaquin and Englund, Dirk R. and Poon, Joyce K. S.},
  title = {AI agents for photonic integrated circuit design automation},
  journal = {APL Machine Learning},
  year = {2025},
  volume = {3},
  number = {4},
  doi = {10.1063/5.0300741}
}
Kostenlos starten →