{"id":"W4417280508","doi":"10.1016/j.watres.2025.125157","title":"Making waves: A conceptual framework exploring how large language model-based multi-agent systems could reshape water engineering","year":2025,"lang":"en","type":"article","venue":"Water Research","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"United Nations University Institute for Water, Environment, and Health","funders":"","keywords":"Conceptual framework; System of systems; Negotiation; Architecture; System of systems engineering; Flood myth","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":[0.005539158,0.0009731241,0.00057411,0.002077418,0.002764422,0.007142332,0.003465938,0.003852561,0.007720411],"category_scores_gemma":[0.006030861,0.0006889373,0.001544612,0.001489135,0.01111971,0.01399733,0.005820236,0.00352967,0.001163459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003055519,"about_ca_system_score_gemma":0.003317966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004705975,"about_ca_topic_score_gemma":0.003230914,"domain_scores_codex":[0.9980856,0.001066841,0.00009593396,0.0002777697,0.0002969529,0.0001769451],"domain_scores_gemma":[0.9973271,0.001325337,0.0002957119,0.0004700038,0.0002556875,0.0003261354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003588209,0.000007340611,0.00006421898,0.00002324033,0.000006363775,0.00004349427,0.0004537099,0.004318244,0.000137351,0.9918697,0.0003782212,0.002694551],"study_design_scores_gemma":[0.00001627949,0.00002342334,0.00005970127,0.0000796508,0.00001565873,0.00005998658,0.0006368795,0.04128368,0.0002745533,0.9191336,0.03839621,0.00002044283],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006005711,0.0009516861,0.9240855,0.007617353,0.0001922696,0.000168026,0.00008492962,0.0003133901,0.06058113],"genre_scores_gemma":[0.4291605,0.001911538,0.5494424,0.001292965,0.0002224521,0.0008917299,0.0001780648,0.0002383543,0.016662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007720411,"threshold_uncertainty_score":0.02929425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2002037649382201,"score_gpt":0.3769499011469604,"score_spread":0.1767461362087403,"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."}}