{"id":"W4410629910","doi":"10.1016/j.neucom.2025.130470","title":"SAGE: Self-evolving Agents with Reflective and Memory-augmented Abilities","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Science and Technology Planning Project of Shenzhen Municipality","keywords":"Computer science; SAGE; Artificial intelligence; Cognitive science; Cognitive psychology; Psychology","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":[0.0003064458,0.0003571089,0.0003531008,0.0001935609,0.0002369193,0.000558757,0.0008410885,0.0006714358,0.003830534],"category_scores_gemma":[0.001476168,0.0001736938,0.000309032,0.0001243212,0.0005573959,0.0006554017,0.001305102,0.00077003,0.00100274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001707975,"about_ca_system_score_gemma":0.0003961165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005904461,"about_ca_topic_score_gemma":0.000975825,"domain_scores_codex":[0.9998916,0.00002703364,0.000007051292,0.00002181523,0.00003906638,0.00001332682],"domain_scores_gemma":[0.9996264,0.0001586032,0.00003067814,0.00006949678,0.0000530936,0.00006168329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004810516,0.0003475738,0.003172707,0.0002870196,0.0001634251,0.0006051032,0.0004309221,0.6414083,0.05100098,0.09485721,0.01236924,0.1948764],"study_design_scores_gemma":[0.0000893225,0.0001501913,0.000286731,0.00001685109,0.00002780809,0.0001481136,0.00003838135,0.9487653,0.01010331,0.03040214,0.009955375,0.00001654258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09570216,0.0002667847,0.8791993,0.000409162,0.0002959381,0.0001447143,0.0001809895,0.007252601,0.01654835],"genre_scores_gemma":[0.7164711,0.0002166386,0.2628723,0.0002029356,0.00004195855,0.0002660329,0.0002968647,0.0003347985,0.0192974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003830534,"threshold_uncertainty_score":0.0128144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00843311187358675,"score_gpt":0.2504298560117046,"score_spread":0.2419967441381178,"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."}}