Preprint
Oct 2026
ORSMT: Unleashing the Potential of Satisfiability Modulo Theories for Semantic Verification and Repair in LLM-Based Optimization
Across 3,034 problems and six generator sizes, ORSMT improves the model-code match rate in all 72 benchmark and generator combinations before selection and raises the aggregate rate from 43.2% to 88.2% and the share that are both correct and matched from 25.2% to 40.2%.
Rui Zhang, Chenyu Zhou, Jiang-Hao Lin et al.
· 0 citations