{"id":"W4417130747","doi":"10.1109/comst.2025.3641591","title":"Mixture of Experts for Decentralized Generative AI and Reinforcement Learning in Wireless Networks: A Comprehensive Survey","year":2025,"lang":"en","type":"article","venue":"IEEE Communications Surveys & Tutorials","topic":"Advanced Data and IoT Technologies","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Wireless network; Wireless; Key (lock); Generative grammar; Adaptability; Resource (disambiguation); Generative model","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":[],"consensus_categories":[],"category_scores_codex":[0.0008792112,0.0001635361,0.000418038,0.0001445876,0.0001237003,0.00002844507,0.0004538525,0.0001477976,0.000001833223],"category_scores_gemma":[0.0004090747,0.0001687067,0.00003604286,0.0003974835,0.0001705723,0.0001529354,0.0001582998,0.0002011617,2.587132e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007779289,"about_ca_system_score_gemma":0.00003776252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002204893,"about_ca_topic_score_gemma":0.001013369,"domain_scores_codex":[0.9984074,0.0006763295,0.0004823197,0.0001558569,0.00006636618,0.0002117221],"domain_scores_gemma":[0.9971132,0.001737773,0.00008870757,0.0008109037,0.0002254765,0.00002393741],"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":[0.0001685312,0.0001648984,0.03981617,0.000282268,0.0005120719,0.000001085353,0.001595391,0.8201952,0.06302779,0.01039621,0.01240487,0.05143553],"study_design_scores_gemma":[0.007066752,0.0002394339,0.08230022,0.000943762,0.0001067229,0.00000215318,0.001409951,0.7630759,0.06805078,0.002264851,0.07309769,0.001441762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.132956,0.007303128,0.8569208,0.0001731698,0.001126667,0.001020696,0.0001047873,0.0002942604,0.0001005017],"genre_scores_gemma":[0.987341,0.008630218,0.003309932,0.00002958029,0.0000235054,0.0002119277,0.0003988199,0.00001718266,0.00003786809],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.854385,"threshold_uncertainty_score":0.687966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04074737434104819,"score_gpt":0.3233127668672785,"score_spread":0.2825653925262303,"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."}}