Formal-Verification-Guided Bayesian Optimization for Non-Intrusive Last-Mile Coverage Closure
This workflow uses a non-intrusive diagnosis-and-search approach to close coverage gaps in hardware verification environments. It maps residual targets to existing testbench knobs using structural analysis (AST/COI) to prune the search space before applying difficulty-conditioned Bayesian Optimization. The process uses formal verification as a diagnostic oracle to classify targets and guide policy routing, successfully achieving high last-mile coverage closure.