{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001873065,0.00209862,0.0009377482,0.001242854,0.0006293565,0.002304361,0.003897454,0.001746463,0.00601095],"category_scores_gemma":[0.0129445,0.0009596947,0.002087862,0.001170745,0.001408094,0.004695608,0.002947906,0.003844249,0.002094446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001719225,"about_ca_system_score_gemma":0.002783321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01235602,"about_ca_topic_score_gemma":0.02899903,"domain_scores_codex":[0.9984583,0.000540397,0.00009557421,0.0004470577,0.0003671968,0.00009149748],"domain_scores_gemma":[0.9935963,0.004333451,0.0002812627,0.001247256,0.0003792015,0.0001624632],"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":[0.000209808,0.0003405525,0.002425315,0.0008623592,0.0001728473,0.0003428058,0.0003547588,0.7025214,0.006028068,0.01931685,0.01649744,0.2509277],"study_design_scores_gemma":[0.0000313924,0.00004176747,0.0001319318,0.00003460572,0.00002259603,0.00005325751,0.0000582485,0.9768522,0.003107008,0.01454381,0.005110089,0.00001312371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03144544,0.0006895537,0.9307094,0.0008149714,0.00007528844,0.0003410866,0.002407651,0.0254552,0.008061376],"genre_scores_gemma":[0.1832872,0.0003485415,0.8058411,0.0003857028,0.00002835301,0.0004091227,0.006169977,0.001482829,0.002047158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01235602,"threshold_uncertainty_score":0.0245682,"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."}}