PICopilot: An LLM-based Agentic Framework for Assisting Photonic Integrated Circuit Design via Script Generation
2026-08-03 • Emerging Technologies
Emerging TechnologiesArtificial Intelligence
AI summaryⓘ
The authors explain that designing photonic integrated circuits (PICs) is moving from easy-to-use visual tools to more complex scripting, which makes creating these designs harder and slower. To help with this, they developed PICopilot, a system that uses smart language models to turn simple instructions into design scripts automatically. This system uses multiple agents and feedback loops to reliably complete tasks and works better than other similar methods, even outperforming a leading model called GPT-5 on many design tasks. Their tests show PICopilot can handle a wide variety of PIC scripting jobs efficiently and accurately.
photonic integrated circuitsscript-based designlarge language modelsdesign automationmulti-agent systemsretrieval-augmented generationprogramming interfaces (APIs)natural language processingGPT-5
Authors
Xiaohan Jiang, Zeyu Li, Wei Zhang, Jiang Xu
Abstract
The rapid development of photonic integrated circuits (PICs) is shifting the design flow from traditional graphical user interface (GUI)-based methods to script-based methods for higher flexibility, portability, and maintainability. However, script-based design introduces new challenges, requiring designers to possess additional proficiency in tool application programming interfaces (APIs) and programming. It also demands greater effort and time because it is inherently less intuitive and more complex than GUI-based methods. As PICs grow in scale and complexity, the productivity gap between design needs and manual scripting capabilities continues to widen. To address this gap, we introduce PICopilot, the first large language model (LLM)-based agentic framework that assists in PIC design via automated design script generation from natural language instructions. PICopilot leverages a multi-agent architecture with a feedback mechanism and a specifically designed retrieval-augmented generation (RAG) pipeline, achieving a high success rate and reliability. Experimental results on a benchmark of diverse PIC scripting tasks demonstrate that PICopilot successfully completes all 48 tasks and outperforms other LLM-based approaches without incurring substantial extra latency or cost, even solving 21 more tasks than the advanced GPT-5 model with a general RAG pipeline.