{"id":"W4408062334","doi":"10.5220/0013303000003890","title":"Toolshed: Scale Tool-Equipped Agents with Advanced RAG-Tool Fusion and Tool Knowledge Bases","year":2025,"lang":"en","type":"article","venue":"","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Computer science; Scale (ratio); Human–computer interaction; Fusion","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":[0.0002113378,0.0002218788,0.0002817783,0.0001332447,0.0002108935,0.0002452926,0.0005810514,0.00007666587,0.00006842276],"category_scores_gemma":[0.0001054254,0.0001566831,0.00004915561,0.0004682652,0.00009139041,0.0006627449,0.0006068978,0.0001007601,0.00004693208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003410922,"about_ca_system_score_gemma":0.0001311618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002919392,"about_ca_topic_score_gemma":0.0001303616,"domain_scores_codex":[0.9985285,0.00005819396,0.0002634556,0.0005851666,0.0001967014,0.0003679547],"domain_scores_gemma":[0.998898,0.0002304069,0.00005492943,0.0006638474,0.0001041547,0.00004869978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001920712,0.0004725316,0.02998334,0.0002164209,0.00007625461,0.00007062092,0.0008965885,0.00004369183,0.005220618,0.05656514,0.0210602,0.8852025],"study_design_scores_gemma":[0.01132171,0.00124073,0.6874563,0.001054153,0.0001428342,0.0001089113,0.001246942,0.1233846,0.05469723,0.01201603,0.1049154,0.002415135],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7577587,0.0004876923,0.2010851,0.0009669989,0.0004662469,0.0003908692,0.000001835638,0.0004195726,0.03842289],"genre_scores_gemma":[0.9254655,0.0001245906,0.06292213,0.001283305,0.00003383546,0.00004028677,0.000003100825,0.000009159554,0.0101181],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8827874,"threshold_uncertainty_score":0.638935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01197985572013135,"score_gpt":0.2638252760733204,"score_spread":0.2518454203531891,"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."}}