{"id":"W4411799318","doi":"10.1109/tpami.2025.3584698","title":"Reinforcement Learning With LLMs Interaction for Distributed Diffusion Model Services","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; Ministry of Science and ICT, South Korea; Ministry of Education - Singapore","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Diffusion; Psychology; Social psychology","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":[0.000165827,0.0002508011,0.0003415676,0.0008518831,0.000493274,0.0003058773,0.0001648579,0.00006373814,0.00006240596],"category_scores_gemma":[0.000004093314,0.000196249,0.0002112304,0.001362179,0.00003439844,0.0004821312,0.000006947595,0.0002124402,0.000007172465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003032245,"about_ca_system_score_gemma":0.00001132942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002836905,"about_ca_topic_score_gemma":0.002339741,"domain_scores_codex":[0.9987697,0.000008108436,0.0003680909,0.0004454722,0.0001948896,0.0002137115],"domain_scores_gemma":[0.9992663,0.00004876241,0.000195665,0.0002053957,0.0002655148,0.00001831526],"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":[0.0001095475,0.00009341776,0.001292488,0.0002201235,0.0005037976,7.052069e-7,0.00003752424,0.8564785,0.00009338225,0.00007472702,0.000003700478,0.1410921],"study_design_scores_gemma":[0.000203913,0.00002075674,0.00011083,0.0001364771,0.002200379,4.190438e-7,0.0002567602,0.9939028,0.00247439,0.0002583789,0.0002178457,0.0002170355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02152442,0.00003675402,0.977443,0.0005173133,0.00007406044,0.0001548614,0.00001209647,0.00009690922,0.0001405699],"genre_scores_gemma":[0.9981099,0.0001230528,0.0001749099,0.0008031916,0.00003726855,0.00007450148,0.0001458925,0.00001568421,0.0005155568],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9772681,"threshold_uncertainty_score":0.8002803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01532205061213469,"score_gpt":0.2555227683951741,"score_spread":0.2402007177830394,"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."}}