{"id":"W4388483618","doi":"10.1109/ase56229.2023.00148","title":"Towards Autonomous Testing Agents via Conversational Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Test strategy; Autonomy; Software testing; Process (computing); Software engineering; Process management; Knowledge management; Human–computer interaction; Data science; Software; Engineering; Programming language; Political science","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":[],"consensus_categories":[],"category_scores_codex":[0.0004445419,0.0001061599,0.00009988545,0.000141832,0.000127666,0.0001006912,0.0005376841,0.00004728703,0.00003570473],"category_scores_gemma":[0.0002897987,0.00009899405,0.00003763969,0.0006665213,0.00001595009,0.000311361,0.0003716691,0.00008501193,0.0002827474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003149733,"about_ca_system_score_gemma":0.00008532065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000221006,"about_ca_topic_score_gemma":0.000002031628,"domain_scores_codex":[0.9989493,0.00002829965,0.0001523997,0.0003014341,0.0002598765,0.0003086951],"domain_scores_gemma":[0.9991947,0.0002259436,0.00004752639,0.0003799847,0.00007917951,0.00007263443],"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":[0.000005771803,0.0002774714,0.01659603,0.0001087583,0.000108117,0.0004729129,0.01347565,0.007810437,0.0008013682,0.1810615,0.3205835,0.4586985],"study_design_scores_gemma":[0.0001099602,0.00002130972,0.002543801,0.00001140106,0.000002320011,0.00001518401,0.000008464162,0.9220273,0.0002602245,0.07456091,0.000311961,0.000127112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005257066,0.00001639168,0.951187,0.0003955961,0.0001628937,0.00008848479,0.000004656084,0.03413894,0.008748933],"genre_scores_gemma":[0.6984534,5.410636e-7,0.3000701,0.0006095886,0.00003818682,0.00001504262,0.000008998127,0.000009225323,0.000794931],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9142169,"threshold_uncertainty_score":0.403686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05764313100772826,"score_gpt":0.2978644873038421,"score_spread":0.2402213562961138,"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."}}