{"id":"W7114912747","doi":"10.1145/3748636.3764603","title":"Learning Heuristics to Solve Dynamic Vehicle Routing Problems Using Large Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Vehicle Routing Optimization Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Toronto; University of Waterloo","funders":"National Research Council Canada","keywords":"Heuristics; Vehicle routing problem; Leverage (statistics); Scalability; Greedy algorithm; Executable; Reinforcement learning; Routing (electronic design automation)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001126798,0.00169209,0.001097125,0.0007521718,0.0004827266,0.001116482,0.002087408,0.001414491,0.00327645],"category_scores_gemma":[0.004728432,0.0009514504,0.001279459,0.0007587445,0.0007864143,0.001379686,0.001081324,0.00216532,0.0009034309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001194516,"about_ca_system_score_gemma":0.002518376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007921115,"about_ca_topic_score_gemma":0.01541055,"domain_scores_codex":[0.999385,0.0002151841,0.0000365271,0.0001740058,0.000104787,0.0000844112],"domain_scores_gemma":[0.9975719,0.001862794,0.0001490375,0.0001508187,0.0001897396,0.00007571638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003820705,0.0001075461,0.0007408728,0.0001241043,0.00004078216,0.00009086415,0.00006493743,0.9140372,0.001073147,0.005319017,0.002467124,0.0758963],"study_design_scores_gemma":[0.00001356707,0.00001520015,0.00003432899,0.000006946206,0.000005672568,0.00001078923,0.00001340304,0.9957297,0.0002629382,0.003491841,0.0004124003,0.000003108017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02766002,0.0004100249,0.9651764,0.0003753414,0.00006609152,0.0001656277,0.0001902266,0.002865464,0.003090743],"genre_scores_gemma":[0.3616999,0.0003727595,0.6319025,0.0004918833,0.00009638282,0.0005873853,0.0008851534,0.0005306973,0.003433412],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007921115,"threshold_uncertainty_score":0.01574999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01381204195917172,"score_gpt":0.2859743451169398,"score_spread":0.2721623031577681,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}