{"id":"W4411811242","doi":"10.1007/978-981-96-8889-0_37","title":"LLM-Based MaSE, A Software Development Framework for Developing Multi-agent Systems","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Public Health Ontario; University of Calgary","funders":"","keywords":"Computer science; Software engineering; Software development; Software; Programming 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00136323,0.0008927101,0.0006297433,0.0008791831,0.0007174579,0.001923583,0.001967586,0.001242359,0.01666618],"category_scores_gemma":[0.003072766,0.00118191,0.001102249,0.0008192409,0.0005492171,0.002525217,0.001898588,0.002928738,0.006929185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007756326,"about_ca_system_score_gemma":0.001276979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001579211,"about_ca_topic_score_gemma":0.003444763,"domain_scores_codex":[0.9992624,0.0002229669,0.00006452952,0.00009688969,0.000294856,0.00005834479],"domain_scores_gemma":[0.9991685,0.000431026,0.00004750906,0.0001491833,0.0001508473,0.00005294512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001240074,0.0001887041,0.0004607844,0.001530559,0.0000875839,0.0004376944,0.0008963234,0.03154043,0.02140411,0.2539068,0.06857982,0.6208432],"study_design_scores_gemma":[0.00009594727,0.00009086643,0.0003712827,0.0004742461,0.00006904242,0.0008875746,0.00008605326,0.1961195,0.02202582,0.0956653,0.6840225,0.0000919037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000662706,0.0002690278,0.982115,0.000136513,0.0000601828,0.00009599178,0.0001774074,0.008363248,0.008119922],"genre_scores_gemma":[0.01241119,0.0005480184,0.9660221,0.0001578604,0.00002676097,0.0003816798,0.001112253,0.002653675,0.01668638],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01666618,"threshold_uncertainty_score":0.05575389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04228735081332768,"score_gpt":0.282321220120623,"score_spread":0.2400338693072953,"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."}}