Optimizing Agent Reliability and Tool Calling Efficiency for Chip Design Using NVIDIA NeMo Gym
Source
developer.nvidia.com
Author
Tanya Lenz
Date
Why it matters
Grading final artifacts with a domain verifier and then rewriting skills and MCP tool descriptions from its diagnostics cut turns by 66% and nearly doubled the score. The method transfers to other engineering agents.
Key takeaways · AI-distilled
The Liberty-file verifier multiplies four pass/fail gates (coverage of every cell and PVT corner, file validity, no new failures versus the reference, and integrity against reused or truncated values) by the fraction of values within tolerance, so any failed gate scores zero.
Tuning ran about 25 rollouts of 1.5 to 2 hours each with Claude Opus 4.8 in Claude Code held fixed, on two cells across 36 PVT corners from the open GF180MCU PDK. Only skills and MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition → tool descriptions changed.
The concrete tool fixes: simplify overlapping file and shell interfaces and define tool inputs with explicit JSON schemas. Output tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → fell from about 81K to 29K alongside the drop in turns.
Final-artifact checks caught errors per-step checks missed, including missing cells and operating conditions, wrong slew thresholds, and timing or power values out of tolerance. Errors often produced plausible output rather than clean failures.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
articleNVIDIA Run:ai Is Now Open Source as Part of NVIDIA DSX AI Factory Platform
articleBuild Applications on NVIDIA BlueField Faster with NVIDIA DOCA Agent Skills
articleAI Native by Design: Lessons Learned from Building NVIDIA TensorRT Model Connect
articleNVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring
