ChatEDA: A Large Language Model Powered Autonomous Agent for EDA (TCAD24)
Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation (NAACL25 Main)
We propose some examples of EDA tool instructions datasets for training AutoMage and ChipLlama models, the controllers of ChatEDA and EDAid, respectively.
ChatEDA-Bench is a comprehensive evaluation benchmark comprising 50 distinct tasks to evaluate the performance of LLMs in automating the EDA flow.
To facilitate a better understanding of the Python-EDA interface document, we provide the API document and the corresponding OpenRoad implementation.
@article{wu2024chateda,
title={{ChatEDA: A Large Language Model Powered Autonomous Agent for EDA}},
author={Wu, Haoyuan and He, Zhuolun and Zhang, Xinyun and Yao, Xufeng and Zheng, Su and Zheng, Haisheng and Yu, Bei},
journal={IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems},
year={2024},
publisher={IEEE}
}
@inproceedings{wu2025EDAid,
title={{Divergent Thoughts toward One Goal: LLM-based Multi-Agent Collaboration System for Electronic Design Automation}},
author={Wu, Haoyuan and Zh
54EE
eng, Haisheng and He, Zhuolun and Yu, Bei},
booktitle={Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics},
year={2025}
}This repo is licensed under the Apache 2.0 License.