MétaCan
Menu
Back to cohort
Record W7117573400 · doi:10.1063/5.0300741

AI agents for photonic integrated circuit design automation

2025· article· en· W7117573400 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueAPL Machine Learning · 2025
Typearticle
Languageen
FieldComputer Science
TopicNeural Networks and Reservoir Computing
Canadian institutionsCanada Research ChairsUniversity of Toronto
FundersNatural Sciences and Engineering Research Council of CanadaMax-Planck-Gesellschaft
KeywordsAutomationPhotonicsElectronic design automationCircuit designIntegrated circuitIntegrated designWork (physics)Design engineer

Abstract

fetched live from OpenAlex

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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.955
Threshold uncertainty score0.496

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.025
GPT teacher head0.281
Teacher spread0.257 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it