{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0135111,0.00110835,0.0006968201,0.001019572,0.001603004,0.005021724,0.002995377,0.00323,0.002451181],"category_scores_gemma":[0.04299242,0.001178993,0.001046416,0.0004823777,0.004628468,0.008403444,0.007806942,0.004545663,0.001277318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001331464,"about_ca_system_score_gemma":0.002459419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00283616,"about_ca_topic_score_gemma":0.003505945,"domain_scores_codex":[0.9860964,0.009941474,0.0004851656,0.0009920982,0.002009262,0.0004755074],"domain_scores_gemma":[0.9727418,0.01658948,0.001634492,0.004836785,0.002876294,0.001321238],"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":[0.0005122352,0.0005962905,0.00849067,0.0006226759,0.0001376985,0.001492004,0.0187678,0.09137108,0.03206412,0.6558124,0.008748897,0.1813842],"study_design_scores_gemma":[0.0001118912,0.0001668069,0.0002902071,0.0001406399,0.00005453542,0.000393443,0.001506543,0.7256148,0.01192818,0.2218799,0.03783145,0.00008167366],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01909145,0.0001347704,0.9720257,0.001365338,0.00004820198,0.0002078134,0.00002892029,0.002117381,0.004980436],"genre_scores_gemma":[0.2614156,0.0001503889,0.7332028,0.0006662609,0.00005225082,0.0004990239,0.000118733,0.000438984,0.003456058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0135111,"threshold_uncertainty_score":0.07145435,"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."}}