{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZSSPAYVHUXBW37S7DZLG66W3OZ","short_pith_number":"pith:ZSSPAYVH","schema_version":"1.0","canonical_sha256":"cca4f062a7a5c36dfe5f1e566f7adb7671028266ad290e5b9e41a6d85d522ee8","source":{"kind":"arxiv","id":"2401.00741","version":3},"attestation_state":"computed","paper":{"title":"ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caishuang Huang, Guanyu Li, Junjie Ye, Qi Zhang, Shihan Dou, Sixian Li, Songyang Gao, Tao Gui, Tao Ji, Xiaoran Fan, Xuanjing Huang, Yilong Wu","submitted_at":"2024-01-01T12:49:36Z","abstract_excerpt":"Existing evaluations of tool learning primarily focus on validating the alignment of selected tools for large language models (LLMs) with expected outcomes. However, these approaches rely on a limited set of scenarios where answers can be pre-determined, diverging from genuine needs. Furthermore, a sole emphasis on outcomes disregards the complex capabilities required for LLMs to effectively use tools. To tackle this issue, we propose ToolEyes, a fine-grained system tailored for the evaluation of the LLMs' tool learning capabilities in authentic scenarios. The system meticulously examines seve"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.00741","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T12:49:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02af2595c5424b938428bb026b935d1b107115a6e7ff9dfc19b9c43d1795d985","abstract_canon_sha256":"50ae2435cb95e505005b30ff94ed2670fcfca0bc920ffc916b333c8b52a64a87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:49.291919Z","signature_b64":"d1QI9pHbWz0AzB1KDhR16ELrli51WWwiedsHexqcZE7WEqvFjTcenI6rF8MHFsVGAs5RCh6ohxLMFVRJfdyPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cca4f062a7a5c36dfe5f1e566f7adb7671028266ad290e5b9e41a6d85d522ee8","last_reissued_at":"2026-07-05T09:44:49.291428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:49.291428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caishuang Huang, Guanyu Li, Junjie Ye, Qi Zhang, Shihan Dou, Sixian Li, Songyang Gao, Tao Gui, Tao Ji, Xiaoran Fan, Xuanjing Huang, Yilong Wu","submitted_at":"2024-01-01T12:49:36Z","abstract_excerpt":"Existing evaluations of tool learning primarily focus on validating the alignment of selected tools for large language models (LLMs) with expected outcomes. However, these approaches rely on a limited set of scenarios where answers can be pre-determined, diverging from genuine needs. Furthermore, a sole emphasis on outcomes disregards the complex capabilities required for LLMs to effectively use tools. To tackle this issue, we propose ToolEyes, a fine-grained system tailored for the evaluation of the LLMs' tool learning capabilities in authentic scenarios. The system meticulously examines seve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00741","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.00741/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.00741","created_at":"2026-07-05T09:44:49.291487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00741v3","created_at":"2026-07-05T09:44:49.291487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00741","created_at":"2026-07-05T09:44:49.291487+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZSSPAYVHUXBW","created_at":"2026-07-05T09:44:49.291487+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZSSPAYVHUXBW37S7","created_at":"2026-07-05T09:44:49.291487+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZSSPAYVH","created_at":"2026-07-05T09:44:49.291487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06566","citing_title":"NTILC: Neural Tool Invocation via Learned Compression","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00933","citing_title":"MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00933","citing_title":"MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZSSPAYVHUXBW37S7DZLG66W3OZ","json":"https://pith.science/pith/ZSSPAYVHUXBW37S7DZLG66W3OZ.json","graph_json":"https://pith.science/api/pith-number/ZSSPAYVHUXBW37S7DZLG66W3OZ/graph.json","events_json":"https://pith.science/api/pith-number/ZSSPAYVHUXBW37S7DZLG66W3OZ/events.json","paper":"https://pith.science/paper/ZSSPAYVH"},"agent_actions":{"view_html":"https://pith.science/pith/ZSSPAYVHUXBW37S7DZLG66W3OZ","download_json":"https://pith.science/pith/ZSSPAYVHUXBW37S7DZLG66W3OZ.json","view_paper":"https://pith.science/paper/ZSSPAYVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00741&json=true","fetch_graph":"https://pith.science/api/pith-number/ZSSPAYVHUXBW37S7DZLG66W3OZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZSSPAYVHUXBW37S7DZLG66W3OZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZSSPAYVHUXBW37S7DZLG66W3OZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZSSPAYVHUXBW37S7DZLG66W3OZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZSSPAYVHUXBW37S7DZLG66W3OZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZSSPAYVHUXBW37S7DZLG66W3OZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZSSPAYVHUXBW37S7DZLG66W3OZ/action/replication_record"}},"created_at":"2026-07-05T09:44:49.291487+00:00","updated_at":"2026-07-05T09:44:49.291487+00:00"}