{"id":"W4389544300","doi":"10.1109/acsos-c58168.2023.00048","title":"Self-Adaptive Large Language Model (LLM)-Based Multiagent Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Adaptation (eye); Conversation; Multi-agent system; Key (lock); Adaptability; Multitude; Distributed computing; Human–computer interaction; Knowledge management; Artificial intelligence; Computer security","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005361944,0.0001544165,0.0001747971,0.0001753771,0.0001382752,0.0001361758,0.0004636519,0.00007573286,0.00001290607],"category_scores_gemma":[0.00001462805,0.0001278997,0.00008130145,0.0004706344,0.000005420176,0.0002920143,0.0001369406,0.00007673456,0.0009367496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007900607,"about_ca_system_score_gemma":0.00006971489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001920708,"about_ca_topic_score_gemma":0.00004113313,"domain_scores_codex":[0.9984493,0.00009713814,0.0002651392,0.0004066334,0.0004035004,0.0003783013],"domain_scores_gemma":[0.9990897,0.00007154357,0.0000980187,0.0005541612,0.00007254478,0.0001140111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002900118,0.00147664,0.001595859,0.0007372448,0.0002613698,0.0003288938,0.02976123,0.4248032,0.01005738,0.4737447,0.05312842,0.004076009],"study_design_scores_gemma":[0.0005391319,0.00003024644,0.0003866032,0.00002092526,0.000004421186,0.000001339473,0.0002882053,0.9965321,0.0008942327,0.0000174078,0.001114352,0.0001710774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01800902,0.00008872605,0.9766724,0.0001699855,0.0005859892,0.0004921086,0.00001508549,0.001578054,0.002388664],"genre_scores_gemma":[0.9724677,0.000004754034,0.02390923,0.000189117,0.00007541222,0.00007231723,0.00001562214,0.00001550206,0.003250316],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9544587,"threshold_uncertainty_score":0.9998412,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0295361948046554,"score_gpt":0.2657220757973752,"score_spread":0.2361858809927198,"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."}}