{"id":"W4401414318","doi":"10.1109/icra57147.2024.10610065","title":"ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planning","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; Natural Sciences and Engineering Research Council of Canada","keywords":"Task (project management); Computer science; Horizon; Time horizon; Artificial intelligence; Mathematical optimization; Engineering; Mathematics; Systems engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003233367,0.0001848792,0.0001699278,0.0001304045,0.000128942,0.0004603225,0.0005102089,0.00008767861,0.00002086546],"category_scores_gemma":[0.00001766473,0.0001581266,0.0001074904,0.0001996546,0.000008715116,0.0006644629,0.000251478,0.0001648865,0.00004575539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007532738,"about_ca_system_score_gemma":0.0001230513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001262178,"about_ca_topic_score_gemma":0.00001849883,"domain_scores_codex":[0.9984624,0.00003114596,0.0002456999,0.0006025477,0.000232412,0.0004257616],"domain_scores_gemma":[0.9993197,0.0000848354,0.00003230034,0.0004196519,0.00005524715,0.00008823422],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003723999,0.0002607112,0.0001621663,0.0004831296,0.0003373375,0.000461428,0.06377667,0.05915393,0.008718894,0.8142865,0.01597212,0.03634982],"study_design_scores_gemma":[0.0002921642,0.00007508908,0.000003880477,0.0000517335,0.00001442892,0.00001128725,0.00009702481,0.9943938,0.001221583,0.002489733,0.001142534,0.0002067951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02073309,0.000405891,0.9737838,0.0006551823,0.0006216121,0.0002727739,0.00002226275,0.0009929636,0.002512437],"genre_scores_gemma":[0.7844894,0.000002338829,0.2095403,0.0004151884,0.000288239,0.00005050477,0.00002029591,0.00002179171,0.005171974],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9352398,"threshold_uncertainty_score":0.6448217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02641663869101564,"score_gpt":0.3070668637932958,"score_spread":0.2806502251022802,"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."}}