Reproduce “An Agentic Python Framework for LLM-Driven UVM Testbench Synthesis with Closed-Loop Compiler Feedback” 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
Vikash Kumar
The authors present a framework that generates UVM testbenches from a structured description of interfaces, protocol rules, and coverage intents, then revises them through compiler-diagnostic and coverage-feedback loops. On one AHB-to-APB bridge, it found an extra APB completion missed by manual and UVMF baselines, and reached 96.8% functional coverage at 24 hours versus 92.7% manually; results cover four tested designs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.