{"id":"W7131998979","doi":"","title":"Enhancing the planning capabilities of large language models by building external world models","year":2025,"lang":"en","type":"article","venue":"NPARC","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Core (optical fiber); Baseline (sea); Plan (archaeology); Automated planning and scheduling; Language model","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001037711,0.0001422006,0.000195355,0.0001369377,0.0002441268,0.0001135054,0.000859425,0.00004584912,0.000017905],"category_scores_gemma":[0.00003509808,0.0001116867,0.00006955772,0.0003589264,0.00004278935,0.0004404095,0.0002640429,0.0002601813,0.000001489207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003767561,"about_ca_system_score_gemma":0.00008730866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001065588,"about_ca_topic_score_gemma":0.00001576077,"domain_scores_codex":[0.9986451,0.0001288054,0.000305918,0.0002920039,0.0002561742,0.0003719456],"domain_scores_gemma":[0.9988092,0.0005096236,0.0001065623,0.0004816696,0.00004977972,0.00004318684],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001840086,0.00006584368,0.0007575857,0.000212657,0.00006275508,0.0000167843,0.03208683,0.1396298,0.1684339,0.6422868,0.007460291,0.008968364],"study_design_scores_gemma":[0.0001925753,0.00001629068,0.00001901886,0.0005323261,0.000009073698,0.00000237142,0.0005579301,0.7852533,0.05940238,0.1536062,0.0002667635,0.0001417818],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08871708,0.001505327,0.8925305,0.0004484761,0.0001529003,0.00009427444,0.00001157699,0.0001098156,0.01643005],"genre_scores_gemma":[0.9393046,0.000003624892,0.05835461,0.0004075732,0.00003161211,0.00001429164,0.000001882687,0.000007806668,0.001873994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8505875,"threshold_uncertainty_score":0.4554452,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01296520347271867,"score_gpt":0.2652528341959908,"score_spread":0.2522876307232721,"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."}}