{"id":"W4414055490","doi":"10.36227/techrxiv.175735299.97215847/v1","title":"Responsible Agentic Reasoning and AI Agents: A Critical Survey","year":2025,"lang":"en","type":"article","venue":"","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute","funders":"HORIZON EUROPE Framework Programme","keywords":"Trustworthiness; Audit; Perception; Knowledge representation and reasoning; Automated 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":[0.01316183,0.001180985,0.001559778,0.008222314,0.001346102,0.007906203,0.002738025,0.00386378,0.002959985],"category_scores_gemma":[0.02414762,0.001364981,0.001042692,0.008400484,0.00474843,0.01504461,0.003016251,0.004718279,0.001340364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004416147,"about_ca_system_score_gemma":0.004352064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003794634,"about_ca_topic_score_gemma":0.0019075,"domain_scores_codex":[0.9877506,0.004784562,0.001362901,0.001208932,0.00435683,0.0005361394],"domain_scores_gemma":[0.9628139,0.02729718,0.001257623,0.002241359,0.00573881,0.0006511608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008535142,0.0001400612,0.003037823,0.0056868,0.0001093156,0.000129917,0.001166973,0.00777287,0.0004422485,0.4409078,0.01845143,0.5220694],"study_design_scores_gemma":[0.00002331194,0.0001956244,0.002168184,0.006737356,0.0001139674,0.0006314121,0.001789435,0.021524,0.001456594,0.378314,0.5869342,0.0001118447],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.004530649,0.8303593,0.118777,0.02048273,0.0008264777,0.0001597683,0.000170481,0.0004929564,0.02420073],"genre_scores_gemma":[0.08126234,0.8128986,0.0953626,0.003591391,0.002739779,0.0003013465,0.0004165524,0.0002912979,0.003136067],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01316183,"threshold_uncertainty_score":0.06960726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02580318371401292,"score_gpt":0.3263356991621448,"score_spread":0.3005325154481319,"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."}}