← Thursday, October 15, 2026AgentsCase study

Siemens EDA cuts agent turns by 66% while raising benchmark scores to 95%

developer.nvidia.com by Tanya Lenz 9 min read Editor score 8/10

Siemens used NeMo Gym verifier diagnostics to refine agent skills and MCP tool descriptions, raising verification scores from about 55% to 95% while cutting turns from 155 to 53. The evaluation loop offers a concrete pattern for improving engineering agents.

What
- NVIDIA NeMo Gym evaluates and improves agents across multistage chip-design workflows using verified final artifacts.
How
- A domain-specific verifier grades Liberty files; its diagnostics guided skill and MCP-description changes, reducing agent turns from 155 to 53.
Why it matters
- Artifact-level evaluation raised Siemens EDA's benchmark score from about 55% to about 95% while reducing turns and output tokens.
rollout tool calls generates checks diagnostics NeMo Gym Siemens Fuse EDAAI Agent characterizationtools Liberty (.lib)files domain-specificverifier
NeMo Gym evaluates the agent’s tool calls and uses verifier results to guide improvements. Sketched from the article's own text.

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.

Your note

Private to you. Stored in this browser, and synced to your account when you are signed in.