ResearchBenchmarksLogistics Optimization Modeling on NLP4LP 264 samples (test)Follow89.02Success RateORThought66.951272.680678.4184.1394Aug 20, 2025Evaluation ResultsMethodMethodLinksSuccess RateDelta vs Standard BaselineORThought2025.0889.0216.29Reflexion2025.0877.654.92CoE2025.08752.27CoT2025.08752.27Standard2025.0872.73—SC2025.0871.211.52OptiMUS2025.0869.423.31ORLM2025.0867.84.93