{"id":"W7114793850","doi":"10.1109/jsac.2025.3642840","title":"<i>LAMeTA</i> : Intent-Aware Agentic Network Optimization via a Large AI Model-Empowered Two-Stage Approach","year":2025,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Software-Defined Networks and 5G","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Electrical, Communications and Cyber Systems; Japan Science and Technology Agency; Nanyang Technological University; Ministry of Education, India; Queen's University; Agency for Science, Technology and Research; Queen's University Belfast; National Science Foundation","keywords":"Reinforcement learning; Generative grammar; Enhanced Data Rates for GSM Evolution; Semantics (computer science); Representation (politics); Function (biology); Selection (genetic algorithm); Feature learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009180456,0.0003091642,0.000410627,0.0005125554,0.0009004516,0.0004644442,0.003361677,0.0001676958,0.00001495079],"category_scores_gemma":[0.0001604828,0.0003010422,0.0001632638,0.003770535,0.00007674459,0.000590356,0.000536816,0.001641325,0.00001030746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003182551,"about_ca_system_score_gemma":0.0003820691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002071363,"about_ca_topic_score_gemma":0.0001120609,"domain_scores_codex":[0.9969402,0.0007082486,0.0008289594,0.000429907,0.0003734066,0.0007193106],"domain_scores_gemma":[0.9960417,0.0004741363,0.0003653671,0.002291793,0.0006460103,0.0001809812],"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":[0.0000292786,0.0006200185,0.001304073,0.000008504309,0.0000871826,0.000005692973,0.0002535676,0.9753717,0.00002412644,0.013787,0.006661148,0.00184769],"study_design_scores_gemma":[0.001129529,0.00005050328,0.0003390132,0.0002090628,0.0000342532,0.00003712493,0.00002675932,0.9919956,0.00002383088,0.004052358,0.001833377,0.0002685515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008113143,0.0008638084,0.9922281,0.00262171,0.0005010625,0.0003712172,0.000008495235,0.0002603795,0.00233391],"genre_scores_gemma":[0.833184,0.0009138913,0.1617106,0.003466965,0.00009776569,0.00008673059,0.00006739142,0.00003271719,0.000439948],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8323727,"threshold_uncertainty_score":0.9999442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02447992465991996,"score_gpt":0.2968168859824573,"score_spread":0.2723369613225374,"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."}}