重點導讀
Siemens EDA 團隊 透過 NVIDIA NeMo Gym 檢查其晶片設計 AI 產出的工程檔，追蹤錯誤並改進 AI 的技能與工具說明，將標準單元特徵化基準的驗證分數從約 55% 提升至 95%，同時減少 66% 的 AI 互動回合與 64% 的輸出 token。
NVIDIA AI@NVIDIAAI
·14 小時前
How do you make a chip design agent more reliable and efficient?
The @Siemens EDA team used NVIDIA NeMo Gym to check the engineering files its agent produced, trace errors, and improve the agent’s skills and tool descriptions.
In its standard cell characterization benchmark, those changes raised the composite verification score from ~55% to ~95%, with 66% fewer agent turns and 64% fewer output tokens.
We just published a new techblog that walks through what the team measured, what they changed, and how other engineering teams can apply the approach → https://t.co/fs0nAEdTtX
推文來源 · X (Twitter)在 X 參與討論