2 papers
cs.SE2026
IR2Solve: Structured Intermediate Representations for Cost-Efficient Optimization Autoformulation
Penglin Zhu, Linhai Zhang, Jungang Xu +2
Large language models (LLMs) can translate natural-language optimization problems into solver-ready formulations, but direct code generation is brittle: schema, indexing, and seman…
cs.AI2026
ModelEquivBench: Certifying Multi-Relational Evaluation of LLM-Generated Optimization Models
Penglin Zhu, Jungang Xu
Large language models increasingly generate optimization models from natural language, but existing evaluation often reduces a generated model and its ground truth to a single equi…