{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001936337,0.0005047989,0.000677138,0.0004017274,0.001139534,0.0005404124,0.0007198054,0.0003581658,0.00003139697],"category_scores_gemma":[0.0003104823,0.0004981949,0.0004647227,0.0007082064,0.0001230171,0.0003755665,0.0003126359,0.0002189084,0.00005800761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008414749,"about_ca_system_score_gemma":0.001789541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008052425,"about_ca_topic_score_gemma":0.00003472462,"domain_scores_codex":[0.9959723,0.0003059952,0.0012459,0.001283778,0.0003281906,0.0008638501],"domain_scores_gemma":[0.9962139,0.00121017,0.0004472441,0.0007309746,0.001158221,0.000239556],"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":[0.002125705,0.006135551,0.003569445,0.03708449,0.004076763,0.00005028342,0.02618228,0.1238523,0.009061887,0.3373715,0.293556,0.1569338],"study_design_scores_gemma":[0.003145812,0.0003402566,0.0009927083,0.001595466,0.0001869848,0.00000473764,0.0004794413,0.9656588,0.001426966,0.0001336585,0.02555192,0.0004832974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006612015,0.001010258,0.987319,0.001147792,0.00384359,0.003076805,0.0004725751,0.001382935,0.001085855],"genre_scores_gemma":[0.8294483,0.000004521876,0.1657854,0.0002070161,0.00009917899,0.0005216379,0.0001581526,0.00002229834,0.003753521],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8418065,"threshold_uncertainty_score":0.999747,"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."}}