Siemens EDA 用 NVIDIA NeMo Gym 把芯片设计智能体验证分数从 55% 提到 95%
Siemens EDA 分享了怎么用 NeMo Gym 调试芯片设计智能体，验证分数从 55% 拉到 95%，还省了 66% 的轮次，写代码的可以看看他们的排查思路。
Siemens EDA 团队用 NVIDIA NeMo Gym 检查其芯片设计智能体生成的工程文件，追踪错误并改进技能与工具描述。在标准单元表征基准上，复合验证分数从约 55% 提升到 95%。同时智能体轮次减少 66%，输出 token 减少 64%。NVIDIA 已发布技术博客，讲解团队的测量方法和可复用的改进流程。
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 → nvda.ws/4Beujcb 💬 23 🔄 19 ❤️ 163 👀 13010 📊 49 ⚡
