AssertLLM2 introduces a benchmark of 83 designs supporting bug-prevention and bug-hunting assertion generation tasks with evaluation across syntactic, formal, coverage, and mutation-based metrics.
Spec2Assertion: Automatic pre- RTL assertion generation using large language models with progressive regularization
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Introduces a quality-aware loop with mutation-guided refinement, RTL-aware solver selection, and causal narrative synthesis to improve LLM-generated assertions for formal verification of RTL designs.
Arcane reduces hardware assertion counts by up to 76.2% via two-tier semantic clustering and MCTS-guided rule exploration while preserving formal coverage and mutation detection, yielding 2.6x-6.1x simulation speedups.
CoverAssert iteratively improves LLM-generated assertions via syntax-semantic clustering and coverage feedback, yielding 9.57% branch, 9.64% statement, and 15.69% toggle coverage gains on four open-source designs when combined with prior tools.
citing papers explorer
-
AssertLLM2: A Comprehensive LLM Benchmark for Assertion Generation from Design Specifications
AssertLLM2 introduces a benchmark of 83 designs supporting bug-prevention and bug-hunting assertion generation tasks with evaluation across syntactic, formal, coverage, and mutation-based metrics.
-
Closing the Loop on LLM-Generated RTL Assertions with Quality-Aware Formal Verification
Introduces a quality-aware loop with mutation-guided refinement, RTL-aware solver selection, and causal narrative synthesis to improve LLM-generated assertions for formal verification of RTL designs.
-
Arcane: An Assertion Reduction Framework through Semantic Clustering and MCTS-Guided Rule Exploring
Arcane reduces hardware assertion counts by up to 76.2% via two-tier semantic clustering and MCTS-guided rule exploration while preserving formal coverage and mutation detection, yielding 2.6x-6.1x simulation speedups.
-
CoverAssert: Iterative LLM Assertion Generation Driven by Functional Coverage via Syntax-Semantic Representations
CoverAssert iteratively improves LLM-generated assertions via syntax-semantic clustering and coverage feedback, yielding 9.57% branch, 9.64% statement, and 15.69% toggle coverage gains on four open-source designs when combined with prior tools.
- From Indiscriminate to Targeted: Functionally Critical Signal-Driven Assertion Generation using LLMs for Efficient RTL Verification