AI Agents for Photonic Integrated Circuit Design Automation
2025/08/18 by Sharma, Ankita, Fu, YuQi, Ansari, Vahid +8 · 3 citations
#Applied Physics (physics.app-ph) #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Physical sciences #Hardware Architecture (cs.AR) #Optics (physics.optics)
paper · doi:10.48550/arxiv.2508.14123
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.
Citations
- Toward Intelligent Electronic-Photonic Design Automation for Large-Scale Photonic Integrated Circuits: from Device Inverse Design to Physical Layout Generation
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Accelerating Photonic Integrated Circuit Design: Traditional, ML and Quantum Methods
- LiDAR 2.0: Hierarchical Curvy Waveguide Detailed Routing for Large-Scale Photonic Integrated Circuits
- Large Language Models and Attention-Based AI for Hardware Design and Security: Progress, Challenges, and Opportunities
- Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
- Accelerating scientific discovery with Co-Scientist
- PICBench: Benchmarking LLMs for Photonic Integrated Circuits Design
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
- Agents for self-driving laboratories applied to quantum computing
- The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
- The Llama 3 Herd of Models
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation
- Autonomous chemical research with large language models
- An autonomous laboratory for the accelerated synthesis of inorganic materials
- ChipNeMo: Domain-Adapted LLMs for Chip Design
- Scientific discovery in the age of artificial intelligence
- VeriGen: A Large Language Model for Verilog Code Generation
- ChipGPT: How far are we from natural language hardware design
- Self-Refine: Iterative Refinement with Self-Feedback
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Self-Instruct: Aligning Language Models with Self-Generated Instructions
- Affective Coherence Monitoring for Transformer-Based Language Models
- Scaling Instruction-Finetuned Language Models
- Distributing Accountability, Not Capability: Phase Separation and the LLM Workflow Quadrant in Autonomous AI Agent Architectures
- Training language models to follow instructions with human feedback
- BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
- Language Models are Few-Shot Learners
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Nanophotonic Inverse Design with SPINS: Software Architecture and Practical Considerations
- Attention Is All You Need
- Meep: A flexible free-software package for electromagnetic simulations by the FDTD method
- OpenAI o1 System Card
Cited by
Related