用自然语言自动生成光子集成电路设计脚本，提升设计效率。
PICopilot: An LLM-based Agentic Framework for Assisting Photonic Integrated Circuit Design via Script Generation
- 基于大模型的多智能体框架，通过反馈机制和检索增强生成实现脚本自动编写。
- 在48个任务中全部成功，比GPT-5多解决21个任务且无额外延迟。
- 适合光子芯片设计人员快速上手，降低编程门槛。
光子集成电路（PIC）的快速发展正推动设计流程从传统的图形化界面（GUI）转向脚本化方法，以提升灵活性、可移植性和可维护性。然而，脚本设计增加了对API和编程技能的要求，使过程更复杂、耗时更长，且随着芯片规模扩大，人工编写脚本的效率与设计需求之间的差距持续拉大。为此，我们提出PICopilot，首个基于大语言模型（LLM）的代理框架，通过自然语言指令自动生成光子集成电路设计脚本。该框架采用多智能体架构与反馈机制，并结合定制的检索增强生成（RAG）管道，实现了高成功率与可靠性。在涵盖多种任务的基准测试中，PICopilot成功完成全部48项任务，优于其他基于LLM的方法，且未带来显著额外延迟或成本；即使在相同条件下，也比采用通用RAG管道的GPT-5多解决了21项任务。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。