{"id":"W7133334912","doi":"10.1109/cins67018.2025.11412089","title":"Knowledge Assistant for Joint Utility: A Multi-Agent LLM-Driven Conversational System for Automated Task Execution","year":2025,"lang":"","type":"article","venue":"","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Task (project management); Workflow; Joint (building); Code (set theory); Software; Natural language; Terminal (telecommunication); Architecture; System integration; Natural language understanding","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":[0.00121029,0.0009754717,0.0004533643,0.0006307046,0.0005746073,0.001220662,0.002218514,0.001070959,0.008220478],"category_scores_gemma":[0.004369046,0.0004711216,0.0004993699,0.000339865,0.0005993102,0.002706543,0.003075248,0.001263247,0.003964627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005552156,"about_ca_system_score_gemma":0.002117566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004071464,"about_ca_topic_score_gemma":0.005080143,"domain_scores_codex":[0.9992854,0.0002317271,0.00004858613,0.0001918923,0.0001685505,0.00007387018],"domain_scores_gemma":[0.9988106,0.000493615,0.0001212551,0.0002462848,0.0001489378,0.00017933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002141384,0.001169278,0.004498187,0.0009493731,0.0001846844,0.001806662,0.005471964,0.0256936,0.07030477,0.02718951,0.08139934,0.7791912],"study_design_scores_gemma":[0.0005477599,0.0006415137,0.002709902,0.0001427763,0.0002109082,0.001147257,0.0009202001,0.743728,0.04650146,0.0368941,0.1662635,0.0002925976],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03340459,0.0002518016,0.8172058,0.0004154461,0.00009174379,0.0004739026,0.0006038896,0.1363519,0.01120089],"genre_scores_gemma":[0.356374,0.0002216729,0.6173471,0.0005982312,0.0000596489,0.000651347,0.001845769,0.003403103,0.01949916],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008220478,"threshold_uncertainty_score":0.02750021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05869483936529245,"score_gpt":0.3075966371326188,"score_spread":0.2489017977673263,"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."}}