{"id":"W4414359780","doi":"10.24963/ijcai.2025/1181","title":"The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Elevator Systems and Control","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Key (lock); Action (physics); Reinforcement learning; Taxonomy (biology); Natural language","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":[0.000134156,0.00005361854,0.00008558265,0.00002647649,0.00006744196,0.00002902378,0.00004711414,0.00002414845,0.00002516682],"category_scores_gemma":[0.00002910773,0.0000330746,0.00001819941,0.00008256638,0.000009752063,0.00002732104,0.000013208,0.0000732568,0.000001985622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009773205,"about_ca_system_score_gemma":0.000008452085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005406844,"about_ca_topic_score_gemma":0.00003145439,"domain_scores_codex":[0.9996561,0.00001014663,0.0001459706,0.00004522235,0.00004948399,0.00009301212],"domain_scores_gemma":[0.9997901,0.00007174166,0.00001453823,0.0000791015,0.00003076377,0.00001375686],"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":[0.00009226141,0.00003738872,0.1452219,0.001214013,0.001607128,0.000007420477,0.002270491,0.2954293,0.09551432,0.2099496,0.05420414,0.1944521],"study_design_scores_gemma":[0.0004796709,0.00003882453,0.003010551,0.0001222551,0.0000166446,8.918468e-7,0.001188746,0.9435835,0.003239321,0.00004654608,0.04817959,0.00009339576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4308885,0.01202063,0.05958848,0.0002741767,0.0006567191,0.0004264713,7.891557e-7,0.0004727827,0.4956715],"genre_scores_gemma":[0.9924859,0.00006983847,0.00002601531,0.00001009444,0.00001095727,0.000007925656,6.011394e-7,0.000004525642,0.007384153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6481543,"threshold_uncertainty_score":0.1348743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002396828550662751,"score_gpt":0.1784749064194855,"score_spread":0.1760780778688228,"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."}}