ResearchBenchmarksLogistics Optimization Modeling on LogiOR 92 samples (test)Follow46.01Success RateORThought14.362822.578930.79539.0111Aug 20, 2025Evaluation ResultsMethodMethodLinksSuccess RateChange vs Baseline (pp)ORThought2025.0846.0112.67CoT2025.0837.323.98Reflexion2025.0836.593.25CoE2025.0834.781.44Standard2025.0833.34—SC2025.0832.251.09ORLM2025.0815.5817.76