{"id":"W4415233743","doi":"10.70777/si.v2i6.16169","title":"Responsible Agentic Reasoning and AI Agents: A Critical Survey","year":2025,"lang":"en","type":"article","venue":"SuperIntelligence - Robotics - Safety & Alignment","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"","keywords":"Operationalization; Intersection (aeronautics); Audit; Trustworthiness; Automated reasoning; Soundness; Class (philosophy)","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":[0.01363238,0.001090697,0.001244299,0.007408735,0.001453833,0.007524652,0.002625566,0.003530313,0.003271989],"category_scores_gemma":[0.02521276,0.00121054,0.0009302225,0.007424341,0.005161513,0.01482438,0.00320776,0.004763539,0.001533973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004650689,"about_ca_system_score_gemma":0.004916355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004164324,"about_ca_topic_score_gemma":0.002314294,"domain_scores_codex":[0.9879742,0.004658588,0.00120433,0.001186844,0.004476084,0.0004999622],"domain_scores_gemma":[0.9634511,0.02633042,0.001229813,0.002336804,0.005956921,0.0006949232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006069315,0.0001095815,0.002438332,0.004518264,0.00008203111,0.0001074737,0.001247003,0.005580563,0.0003727705,0.5076455,0.01588745,0.4619502],"study_design_scores_gemma":[0.00001687086,0.0001263136,0.001501066,0.005656178,0.0000828799,0.0005065089,0.001512909,0.01575899,0.001329355,0.4089875,0.5644422,0.00007932968],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004585958,0.7534716,0.1806554,0.02348295,0.0009331069,0.0001796336,0.0001936843,0.0006526822,0.0358449],"genre_scores_gemma":[0.09555238,0.7500976,0.1421157,0.004090615,0.002529937,0.00037861,0.0005433662,0.0004089045,0.004282926],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01363238,"threshold_uncertainty_score":0.07209575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02827062175905466,"score_gpt":0.3202839762963827,"score_spread":0.292013354537328,"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."}}