{"id":"W4415871599","doi":"10.36227/techrxiv.174612962.26131807/v4","title":"LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Face (sociological concept); Reliability (semiconductor); Field (mathematics); Identification (biology); Action (physics)","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001288852,0.0002663929,0.0002945012,0.0003955981,0.0006609979,0.001487632,0.0004850907,0.0001480648,0.00006213576],"category_scores_gemma":[0.0002962607,0.0002787336,0.00004179242,0.001690171,0.00008545138,0.0004428259,0.0002445408,0.0003274333,0.0000892807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002741585,"about_ca_system_score_gemma":0.0003791756,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01556258,"about_ca_topic_score_gemma":0.002062844,"domain_scores_codex":[0.9970258,0.0009568717,0.0006311134,0.0008312672,0.0002809439,0.0002739738],"domain_scores_gemma":[0.9975394,0.0005932953,0.0002881813,0.0008511199,0.0006085405,0.0001194666],"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":[0.0001629794,0.002287347,0.2533732,0.001203149,0.0003389399,0.000007215854,0.002414976,0.1505961,0.007003262,0.497012,0.01430574,0.07129511],"study_design_scores_gemma":[0.0004988623,0.0001058677,0.2223901,0.0001359507,0.00002164207,0.00000112167,0.00009908345,0.7737767,0.0001934111,0.0001142109,0.002471229,0.0001917787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1710466,0.0003519979,0.8160138,0.005008223,0.001291246,0.001143251,0.00002067124,0.0002364327,0.004887882],"genre_scores_gemma":[0.993551,0.00001279444,0.003189841,0.0003889991,0.00004624088,0.0001539911,0.00005542317,0.00001199956,0.002589707],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8225045,"threshold_uncertainty_score":0.9999665,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02847485938819361,"score_gpt":0.3582016073138506,"score_spread":0.329726747925657,"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."}}