{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002451662,0.0002602458,0.000315459,0.0006039928,0.0004182947,0.0008363016,0.001066699,0.0001976798,0.00002175762],"category_scores_gemma":[0.0001235859,0.0001770906,0.0001053166,0.0003817337,0.00005195715,0.0005861468,0.0007255339,0.0007296911,0.0001519115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002740947,"about_ca_system_score_gemma":0.00006750696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008834302,"about_ca_topic_score_gemma":0.000009715084,"domain_scores_codex":[0.9962526,0.0003580801,0.0003785093,0.0007349781,0.0009683146,0.001307526],"domain_scores_gemma":[0.998485,0.0001065168,0.00003505227,0.0009792427,0.0002507454,0.0001433904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000101805,0.0006079677,0.002138646,0.002583031,0.0002935051,0.0005287388,0.123865,0.257531,0.5297261,0.07856119,0.002371833,0.001691114],"study_design_scores_gemma":[0.0006055818,0.00003042872,0.00006375018,0.0006000825,0.000004164801,0.000001673309,0.001129413,0.9261181,0.06606755,0.00002842912,0.005119992,0.0002308116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.178557,0.000332727,0.8184621,0.0008139593,0.000799956,0.000685258,0.000008473336,0.0002541557,0.00008637246],"genre_scores_gemma":[0.9876513,0.000007729981,0.009727923,0.0001021132,0.0001652381,0.0004101397,0.00001929219,0.00003434192,0.001881893],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8090944,"threshold_uncertainty_score":0.8064476,"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."}}