LayoutCopilot: An LLM-powered Multi-agent Collaborative Framework for Interactive Analog Layout Design
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913645380763648 |
|---|---|
| author | Liu, Bingyang Zhang, Haoyi Gao, Xiaohan Kong, Zichen Tang, Xiyuan Lin, Yibo Wang, Runsheng Huang, Ru |
| author_facet | Liu, Bingyang Zhang, Haoyi Gao, Xiaohan Kong, Zichen Tang, Xiyuan Lin, Yibo Wang, Runsheng Huang, Ru |
| contents | Analog layout design heavily involves interactive processes between humans and design tools. Electronic Design Automation (EDA) tools for this task are usually designed to use scripting commands or visualized buttons for manipulation, especially for interactive automation functionalities, which have a steep learning curve and cumbersome user experience, making a notable barrier to designers' adoption. Aiming to address such a usability issue, this paper introduces LayoutCopilot, a pioneering multi-agent collaborative framework powered by Large Language Models (LLMs) for interactive analog layout design. LayoutCopilot simplifies human-tool interaction by converting natural language instructions into executable script commands, and it interprets high-level design intents into actionable suggestions, significantly streamlining the design process. Experimental results demonstrate the flexibility, efficiency, and accessibility of LayoutCopilot in handling real-world analog designs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_18873 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LayoutCopilot: An LLM-powered Multi-agent Collaborative Framework for Interactive Analog Layout Design Liu, Bingyang Zhang, Haoyi Gao, Xiaohan Kong, Zichen Tang, Xiyuan Lin, Yibo Wang, Runsheng Huang, Ru Hardware Architecture Analog layout design heavily involves interactive processes between humans and design tools. Electronic Design Automation (EDA) tools for this task are usually designed to use scripting commands or visualized buttons for manipulation, especially for interactive automation functionalities, which have a steep learning curve and cumbersome user experience, making a notable barrier to designers' adoption. Aiming to address such a usability issue, this paper introduces LayoutCopilot, a pioneering multi-agent collaborative framework powered by Large Language Models (LLMs) for interactive analog layout design. LayoutCopilot simplifies human-tool interaction by converting natural language instructions into executable script commands, and it interprets high-level design intents into actionable suggestions, significantly streamlining the design process. Experimental results demonstrate the flexibility, efficiency, and accessibility of LayoutCopilot in handling real-world analog designs. |
| title | LayoutCopilot: An LLM-powered Multi-agent Collaborative Framework for Interactive Analog Layout Design |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2406.18873 |