Back to AI News
arxiv

Meta-RTL Evolves Agent Harnesses for RTL Optimization

Meta-RTL is an EDA-grounded framework that evolves RTL optimization harnesses from a minimal loop while keeping the optimization model, EDA flow, and per-design budgets fixed. Compared with Dr. RTL, Meta-RTL* reduces aggregate WNS/TNS violations by 7.8%/11.0% across 20 development designs, with area reductions on 70% of them. Without further evolution, it transfers to 10 unseen IC-RTL designs, reducing aggregate WNS/TNS violations by 20.5%/14.0% and total synthesized area by 12.6%. The paper characterizes three search mechanisms in the evolved harness and assesses their contributions through ablations and a case study.

AI Brief

It shows a concrete method for automatically evolving LLM-agent search procedures for hardware RTL optimization, with reported gains and transfer to unseen designs.

arXiv:2611.25891v1 Announce Type: new Abstract: Large language models enable agents to optimize RTL using EDA feedback, yet their executable search procedures remain largely hand- engineered. We present Meta-RTL, an EDA-grounded framework that evolves RTL optimization harnesses from a minimal loop while keeping the optimization model, EDA flow, and per-design budgets fixed. Compared with Dr. RTL, Meta-RTL* reduces aggregate WNS/TNS violations by 7.8%/11.0% across 20 development designs, with area reductions on 70% of them. Without further evolution, Meta-RTL* transfers to 10 unseen IC-RTL designs, reducing aggregate WNS/TNS violations by 20.5%/14.0% and total synthesized area by 12.6%. We further characterize three search mechanisms in the evolved harness and assess their contributions through ablations and a case study.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!