{"id":"W7091186806","doi":"","title":"Automating Structural Engineering Workflows with Large Language Model Agents","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Workload; Software deployment; Reliability (semiconductor); Key (lock); Core (optical fiber); Concurrent engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001281012,0.0001240787,0.0001264546,0.00008565076,0.0001123651,0.00007238983,0.0003329956,0.00004394499,0.000009077618],"category_scores_gemma":[0.00002244071,0.0001018826,0.00003518061,0.0002809403,0.000004663753,0.0003448967,0.0001251646,0.0001005688,0.00001987832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004370631,"about_ca_system_score_gemma":0.00003008449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003129483,"about_ca_topic_score_gemma":0.0000206075,"domain_scores_codex":[0.9991404,0.00001935445,0.0001757959,0.0002577524,0.0001525142,0.000254182],"domain_scores_gemma":[0.9994843,0.0000247407,0.00006459765,0.0003520819,0.00002861675,0.00004568509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007945853,0.00005213777,0.8600852,0.0002312733,0.0001235303,0.00004952476,0.007053313,0.100302,0.0136132,0.01127153,0.0005729757,0.006637323],"study_design_scores_gemma":[0.0002756219,0.000006155715,0.189692,0.00008467851,0.000004287675,0.000001668781,0.00002460847,0.8087711,0.0009940019,0.000007457876,0.00004091052,0.00009745857],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6441284,0.00005641247,0.3550895,0.00006473888,0.0001841144,0.00009688845,0.000001183652,0.0001885763,0.0001902011],"genre_scores_gemma":[0.9839113,9.372316e-7,0.01514099,0.0001572763,0.00004252879,0.00001240158,0.000004123436,0.000008559135,0.0007218301],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7084691,"threshold_uncertainty_score":0.4154653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01628947537143142,"score_gpt":0.2578200768984144,"score_spread":0.241530601526983,"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."}}