{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001185908,0.0006747115,0.0007130182,0.0003149426,0.0004375534,0.0007128416,0.001392165,0.0007942485,0.002084538],"category_scores_gemma":[0.003945208,0.0003049655,0.0004926337,0.0002951788,0.0008188612,0.001086291,0.001451252,0.001508103,0.0003515798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001217491,"about_ca_system_score_gemma":0.001130428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006400721,"about_ca_topic_score_gemma":0.006696846,"domain_scores_codex":[0.9992875,0.0002792414,0.00002782136,0.0001461715,0.0001557056,0.0001034986],"domain_scores_gemma":[0.9986639,0.0008341888,0.0001194889,0.0001026498,0.0001747795,0.0001049803],"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":[0.0001009192,0.00009570475,0.0008605325,0.00003896692,0.0000314127,0.00009523223,0.0001532292,0.9347743,0.00268549,0.01584059,0.001231957,0.04409163],"study_design_scores_gemma":[0.000005533488,0.000008888414,0.00001876373,6.681732e-7,0.0000019298,0.000004541637,0.000003906632,0.9978483,0.0001655103,0.001798771,0.000141464,0.000001703413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02473828,0.0001365321,0.9723718,0.0003223191,0.00003399996,0.00003814725,0.00002036624,0.0006542479,0.001684242],"genre_scores_gemma":[0.9340022,0.00007264254,0.06324045,0.0001995101,0.00002901383,0.00009103147,0.00004476816,0.00006892326,0.002251458],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006400721,"threshold_uncertainty_score":0.01272696,"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."}}