TriVAL performs construct-validate-revise validation at semantic specification, mathematical formulation, and code generation stages for automatic optimization modeling and introduces the NL4COP benchmark of 150 instances across 50 problem types.
Learning to solve large-scale security-constrained unit commitment problems
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Feasibility-aware imitation learning accelerates Benders decomposition by predicting feasible integer assignments in the master problem, improving solution times over prior imitation learning methods while retaining finite convergence.
citing papers explorer
-
TriVAL: A Tri-Validation Framework for Faithful Automatic Optimization Modeling
TriVAL performs construct-validate-revise validation at semantic specification, mathematical formulation, and code generation stages for automatic optimization modeling and introduces the NL4COP benchmark of 150 instances across 50 problem types.
-
Feasibility-Aware Imitation Learning for Benders Decomposition
Feasibility-aware imitation learning accelerates Benders decomposition by predicting feasible integer assignments in the master problem, improving solution times over prior imitation learning methods while retaining finite convergence.