{"id":"W4417282753","doi":"10.1109/pimrc62392.2025.11274561","title":"Foundation Model-Aided Deep Reinforcement Learning for RIS-Assisted Wireless Communication","year":2025,"lang":"","type":"article","venue":"","topic":"Advanced Wireless Communication Technologies","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ericsson (Canada); University of Ottawa","funders":"","keywords":"Reinforcement learning; Wireless; Beamforming; Overhead (engineering); Wireless network; Channel (broadcasting); Process (computing); Software deployment","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"],"consensus_categories":[],"category_scores_codex":[0.0005331355,0.0005137269,0.0005835263,0.0005723395,0.001085605,0.0002228773,0.001576688,0.0005043482,0.00009103142],"category_scores_gemma":[0.0004404637,0.0006202051,0.0002103415,0.0009476648,0.0002413393,0.0007679316,0.0008030511,0.0009325106,0.00004030872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001015565,"about_ca_system_score_gemma":0.0001266585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004558434,"about_ca_topic_score_gemma":0.0001361495,"domain_scores_codex":[0.9972263,0.0001333941,0.00130487,0.0004670133,0.0002606243,0.0006077738],"domain_scores_gemma":[0.99569,0.0007745111,0.0004112111,0.002524577,0.0005326957,0.00006695887],"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":[0.00004399119,0.00004360981,0.00003572357,0.0002501303,0.0001406182,5.919026e-8,0.0002383512,0.6662123,0.002445822,0.1290746,0.0001568326,0.201358],"study_design_scores_gemma":[0.001453186,0.0000599743,0.0001001617,0.0003853441,0.00009149915,6.306405e-7,0.001623656,0.9617441,0.01568046,0.01299858,0.00533394,0.0005284193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00298983,0.00180253,0.9704342,0.001619096,0.000198609,0.001635944,0.000001402396,0.002048775,0.01926955],"genre_scores_gemma":[0.8890657,0.007076181,0.09699903,0.0001011639,0.00001116583,0.0009566142,0.0003329182,0.00007898571,0.005378232],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8860759,"threshold_uncertainty_score":0.9996249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.025671321809803,"score_gpt":0.2904073887885628,"score_spread":0.2647360669787598,"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."}}