{"id":"W4416082371","doi":"10.36227/techrxiv.175735299.97215847/v2","title":"Responsible Agentic Reasoning and AI Agents: A Critical Survey","year":2025,"lang":"","type":"preprint","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"HORIZON EUROPE Framework Programme; European Commission","keywords":"Trustworthiness; Audit; Automated reasoning; Perception; Knowledge representation and reasoning","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":[0.01267202,0.0009955515,0.001230028,0.007537254,0.001373532,0.007610431,0.002264566,0.003504301,0.002915564],"category_scores_gemma":[0.02147559,0.001167792,0.0008989691,0.007354786,0.005084211,0.0142194,0.002810948,0.00466015,0.001176011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004646687,"about_ca_system_score_gemma":0.004575693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003975716,"about_ca_topic_score_gemma":0.002228775,"domain_scores_codex":[0.989417,0.004313374,0.001055076,0.0009837232,0.003768686,0.0004622161],"domain_scores_gemma":[0.9663066,0.02510281,0.001139931,0.001975148,0.004875737,0.0005997702],"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":[0.00005697325,0.0001177434,0.002404897,0.004205334,0.00007940881,0.0001027436,0.001162762,0.005450113,0.0003385915,0.5358241,0.01540566,0.4348516],"study_design_scores_gemma":[0.00001805285,0.0001246937,0.001645029,0.005366131,0.00008386938,0.00045014,0.001468726,0.01664667,0.001171628,0.4506516,0.5222943,0.00007914821],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004569234,0.7933063,0.1430316,0.02533503,0.0008442321,0.0001624945,0.0001636238,0.0005063605,0.03208115],"genre_scores_gemma":[0.09244407,0.7831928,0.1132902,0.003762471,0.002537137,0.0003243501,0.0003949689,0.0002922345,0.003761751],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01267202,"threshold_uncertainty_score":0.06701684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08589055885772025,"score_gpt":0.3903731380859501,"score_spread":0.3044825792282299,"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."}}