{"id":"W4411604664","doi":"10.1007/978-981-96-1741-8_25","title":"From Novice to Expert: On-the-Job Learning of Autonomous LLM Agents in White-Collar Labor","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"AI in Service Interactions","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Collar; White (mutation); Labour economics; Business; Computer science; Economics; Finance; Biology","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":[0.0008361848,0.0001995704,0.0001688273,0.0001786686,0.001110849,0.001621869,0.0007357204,0.0008114874,0.005447277],"category_scores_gemma":[0.002958589,0.0001193699,0.0001221105,0.0001631919,0.0008819229,0.002163856,0.001580178,0.001190635,0.0008668111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007724035,"about_ca_system_score_gemma":0.0009335694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003823343,"about_ca_topic_score_gemma":0.01002166,"domain_scores_codex":[0.9997774,0.00009734632,0.000005063212,0.0000331808,0.00003248365,0.00005456813],"domain_scores_gemma":[0.9987191,0.000639991,0.00007054496,0.00008570272,0.00009722807,0.000387402],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001116642,0.003887702,0.0623061,0.0002270273,0.0000405422,0.001889385,0.06189908,0.02179688,0.004587081,0.1563123,0.05943986,0.6264974],"study_design_scores_gemma":[0.0001770319,0.00191965,0.07343134,0.0004495201,0.00004014354,0.0006818637,0.1272564,0.1743786,0.007868333,0.5006701,0.1129803,0.0001467452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8397006,0.0007022369,0.01836348,0.00561703,0.0001035603,0.00006148896,0.00006704527,0.000124748,0.1352598],"genre_scores_gemma":[0.9681549,0.0001903598,0.004478946,0.0002534354,0.00001507953,0.00002103179,0.00006731816,0.00001483225,0.02680413],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005447277,"threshold_uncertainty_score":0.01822293,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01716100090819993,"score_gpt":0.258009120598599,"score_spread":0.2408481196903991,"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."}}