Reproduce “Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Wenji Fang, Yao Lu, Jinghua Wang, Zhiyao Xie

Dr. RTL optimizes RTL through a closed loop that analyzes synthesized timing reports, generates parallel candidates, and evaluates them with synthesis and sequential equivalence checking. On 20 human-written designs, it improved average WNS and TNS by 21.3% and 16.9% and reduced area by 5.8% under a commercial synthesis flow; these results do not establish faster clock frequency or search.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.