# PICopilot: An LLM-based Agentic Framework for Assisting Photonic Integrated Circuit Design via Script Generation

arXiv: https://arxiv.org/abs/2608.01791 · HTML: https://mlsanity.com/paper/2608.01791/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 40 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 11 of 11)

- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving](https://mlsanity.com/paper/2504.02605/) (2025)
- [EmbeddingGemma: Powerful and Lightweight Text Representations](https://mlsanity.com/paper/2509.20354/) (2025)
- [ChatEDA: A Large Language Model Powered Autonomous Agent for EDA](https://mlsanity.com/paper/2308.10204/) (2023)
- [AnalogCoder: Analog Circuit Design via Training-Free Code Generation](https://mlsanity.com/paper/2405.14918/) (2024)
- [CoIR: A Comprehensive Benchmark for Code Information Retrieval Models](https://mlsanity.com/paper/2407.02883/) (2024)
- [A Survey of Research in Large Language Models for Electronic Design Automation](https://mlsanity.com/paper/2501.09655/) (2025)
- [DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent](https://mlsanity.com/paper/2412.05311/) (2024)
- [MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization](https://mlsanity.com/paper/2507.19570/) (2025)
- [AI Agents for Photonic Integrated Circuit Design Automation](https://mlsanity.com/paper/2508.14123/) (2025)
- [PICBench: Benchmarking LLMs for Photonic Integrated Circuits Design](https://mlsanity.com/paper/2502.03159/) (2025)

## Abstract (arXiv)

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.