{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002138953,0.0003389722,0.0003552858,0.0003381371,0.0005297184,0.0004219429,0.0005877258,0.0001564509,0.00001235749],"category_scores_gemma":[0.0001112721,0.000312441,0.0002740346,0.0006510935,0.00005783476,0.0002937083,0.0002104024,0.0003346821,0.00007067579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000292675,"about_ca_system_score_gemma":0.0006965024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001928337,"about_ca_topic_score_gemma":0.00001811389,"domain_scores_codex":[0.9978169,0.0001662602,0.0004729347,0.0008168122,0.0002527147,0.0004743658],"domain_scores_gemma":[0.9985975,0.0001208056,0.0002258204,0.0005075707,0.0004401181,0.0001081544],"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":[0.00002927345,0.0009841499,0.0003314986,0.0003959199,0.0001563609,9.410463e-7,0.004797553,0.03580528,0.004096754,0.4817169,0.002103385,0.4695819],"study_design_scores_gemma":[0.000532827,0.0001937257,0.001698631,0.0004906366,0.00003765313,0.000006615482,0.0004257489,0.8477851,0.003823226,0.0005644944,0.1441431,0.0002981772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03599791,0.0001300183,0.9510446,0.0009762134,0.008233693,0.001128039,0.000004206889,0.0006632849,0.001822013],"genre_scores_gemma":[0.8452558,0.000007135585,0.08289543,0.0003081743,0.0008452855,0.0001528537,0.00001097713,0.00002229908,0.07050208],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8681492,"threshold_uncertainty_score":0.9999328,"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."}}