{"id":"W7106260558","doi":"10.2139/ssrn.5784417","title":"Hybrid Multi-Agent AI/MCTS Systems for Complex Information-Imperfect Games","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perfect information; Adversary; Modular design; Reinforcement learning; Set (abstract data type); Monte Carlo tree search; Adaptation (eye); Imperfect","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","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.007312187,0.001387739,0.001648186,0.001235772,0.00176895,0.004041019,0.006094268,0.0005739728,0.00005193729],"category_scores_gemma":[0.001032175,0.001373392,0.00137836,0.0006338119,0.0003509747,0.002786506,0.00193573,0.008607822,0.000406067],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.006700885,"about_ca_system_score_gemma":0.02519279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008384355,"about_ca_topic_score_gemma":0.0004200552,"domain_scores_codex":[0.9849246,0.0007661642,0.00369956,0.001322072,0.00148122,0.007806411],"domain_scores_gemma":[0.9916888,0.0008099629,0.002578862,0.001831824,0.002574041,0.0005165119],"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":[0.0002808234,0.0005317355,0.0003244051,0.001058817,0.002336628,0.00001536651,0.004260046,0.1735223,0.0001085356,0.46095,0.007172584,0.3494388],"study_design_scores_gemma":[0.0007984711,0.000832924,0.00006691094,0.0009170949,0.0002483111,0.0009705769,0.002544463,0.8077934,0.0006556948,0.1043328,0.07949232,0.001347045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002926062,0.01103922,0.9680925,0.002672168,0.01108165,0.003315669,0.000189852,0.0002127836,0.0004700651],"genre_scores_gemma":[0.9467515,0.03324119,0.008924166,0.001377565,0.00210567,0.000582803,0.0001394897,0.00008942613,0.006788142],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9591684,"threshold_uncertainty_score":0.9998873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03813081852907227,"score_gpt":0.315057956466393,"score_spread":0.2769271379373207,"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."}}