An LLM agentic framework with SMT verification generates valid barrier certificates for more than 90 percent of systems in the new BarrierBench dataset spanning linear, nonlinear, discrete, and continuous cases.
CRITICAL:Use ONLY real numbers in the barrier expression
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BarrierBench: Evaluating Large Language Models for Safety Verification in Dynamical Systems
An LLM agentic framework with SMT verification generates valid barrier certificates for more than 90 percent of systems in the new BarrierBench dataset spanning linear, nonlinear, discrete, and continuous cases.