# Siemens EDA uses NeMo Gym to lift chip design agent verification scores

> Original title: How do you make a chip design agent more reliable and efficient?

- Source: NVIDIA AI
- Published: 2026-10-30T18:30:36.000Z
- Bad Influence: https://badinfluence.news/items/fmi829dyjtu39xd1d1btc43zy
- Original: https://x.com/NVIDIAAI/status/2116236342653026706

## Summary

The Siemens EDA team used NVIDIA NeMo Gym to check its chip design agent's engineering files, trace errors, and refine the agent's skills and tool descriptions. On a standard cell characterization benchmark, the changes raised the composite verification score from about 55% to 95%, with 66% fewer agent turns and 64% fewer output tokens.

## Post

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://nvda.ws/4Beujcb

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHV5hjyXbUAEH7dA.jpg&mode=thumb&exp=1793577600&sig=4ae4be4f407d2914)