{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001753993,0.0004223152,0.0004860887,0.0002369125,0.0005387939,0.0004823691,0.001199018,0.0001766684,0.000121434],"category_scores_gemma":[0.001263521,0.0004068125,0.0001454772,0.0009092567,0.0003306117,0.0004791987,0.001148003,0.0003457383,0.0001629114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002687029,"about_ca_system_score_gemma":0.0003890035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001889031,"about_ca_topic_score_gemma":0.0001258329,"domain_scores_codex":[0.996265,0.0005263743,0.0007080091,0.001081424,0.0005182147,0.0009009768],"domain_scores_gemma":[0.9972624,0.0009239914,0.00006679472,0.001122147,0.0002748262,0.0003498423],"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":[0.0001072032,0.0003711572,0.01693825,0.0001334408,0.0001323134,0.0001193947,0.001920423,0.004643952,0.00031035,0.9616079,0.001734825,0.01198073],"study_design_scores_gemma":[0.001953227,0.001373423,0.186291,0.001880733,0.0003369996,0.0002962219,0.00170756,0.5961468,0.02261992,0.13107,0.05240444,0.003919701],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003622492,0.00159856,0.9837622,0.002935394,0.001523141,0.0004056073,0.00001284582,0.0002205441,0.005919202],"genre_scores_gemma":[0.9534121,0.001025356,0.04135245,0.001311166,0.00006385487,0.00003207259,0.00001395284,0.00002713667,0.002761896],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9497896,"threshold_uncertainty_score":0.9998384,"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."}}