Beyond Objective Equivalence: Constraint Injection for LLM-Based Optimization Modeling on Vehicle Routing Problems

Excerpt

arXiv:2606.04816v2 Announce Type: replace Abstract: Large language models (LLMs) can generate executable solver code from natural-language descriptions of optimization problems. However, existing verification signals focus on whether the generated formulation produces the correct objective value. Such signals can overlook constraint-level errors: incorrect formulations may still produce the same optimum when extra or missing constraints do not affect the tested instance. We propose constraint in