AgentDV lifts RTL testbench generation from zero valid environments to 100% pass on four DUTs.

Single-shot prompting produced not one valid coverage-producing verification environment on the paper's benchmarks. AgentDV closes the loop with runnability filtering, CSR-grounded checking to cut hallucinated signals, and coverage-guided iteration against measured gaps. Using Claude Sonnet 4.6 it reaches 100% pass on four design-under-test blocks and 80.9% average across all of them, with 74.5% line and 88.4% branch coverage, against 58.7% and 60.6% average pass rates for Llama and Qwen. (arXiv 2608.27148)