{"id":"W7129249391","doi":"10.1109/icaice68195.2025.11382371","title":"LLM-Driven Multi-Agent Architecture for Automated Physical Education Instruction","year":2025,"lang":"","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Workflow; Pipeline (software); Reliability (semiconductor); Weighting; Architecture; Relevance (law); Systems architecture; Emulation; A priori and a posteriori","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004553346,0.0003443156,0.0002423497,0.0002823636,0.0003341881,0.0006926041,0.001352527,0.0006145882,0.002909238],"category_scores_gemma":[0.0007110894,0.0002480619,0.0003003018,0.00016232,0.0004014514,0.0006758641,0.001131331,0.0006034091,0.0009429439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006523883,"about_ca_system_score_gemma":0.001119627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002691421,"about_ca_topic_score_gemma":0.003821057,"domain_scores_codex":[0.9997898,0.00005797512,0.0000178164,0.00004904591,0.00006100609,0.00002447119],"domain_scores_gemma":[0.9998457,0.00003437041,0.00001931988,0.00003890595,0.00004116095,0.00002051138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003259001,0.0003443862,0.003370754,0.0004031562,0.00009967194,0.0004565662,0.0007810734,0.4720975,0.09371954,0.06067225,0.006174037,0.3615552],"study_design_scores_gemma":[0.00001858995,0.00007492,0.0003735273,0.00001945807,0.00001859156,0.00005133359,0.0000360278,0.9699237,0.01008393,0.008333325,0.01105045,0.00001620469],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01647585,0.0001231816,0.975482,0.000151755,0.00002506946,0.0001102767,0.00005347295,0.00400899,0.003569277],"genre_scores_gemma":[0.4125082,0.0001282708,0.5813212,0.0001036896,0.00001352635,0.0003371072,0.000217897,0.0001607453,0.00520944],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002909238,"threshold_uncertainty_score":0.009732366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02012289491514922,"score_gpt":0.3122613821307259,"score_spread":0.2921384872155766,"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."}}