{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3KHTVI32RWK3GZR4YZJOTVRGVS","short_pith_number":"pith:3KHTVI32","schema_version":"1.0","canonical_sha256":"da8f3aa37a8d95b3663cc652e9d626ac8f2cee03f8354865d81ff55d940488dc","source":{"kind":"arxiv","id":"2407.08713","version":2},"attestation_state":"computed","paper":{"title":"GTA: A Benchmark for General Tool Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cailian Chen, Jize Wang, Kai Chen, Songyang Zhang, Xinyi Le, Yining Li, Zerun Ma","submitted_at":"2024-07-11T17:50:09Z","abstract_excerpt":"Significant focus has been placed on integrating large language models (LLMs) with various tools in developing general-purpose agents. This poses a challenge to LLMs' tool-use capabilities. However, there are evident gaps between existing tool-use evaluations and real-world scenarios. Current evaluations often use AI-generated queries, single-step tasks, dummy tools, and text-only interactions, failing to reveal the agents' real-world problem-solving abilities effectively. To address this, we propose GTA, a benchmark for General Tool Agents, featuring three main aspects: (i) Real user queries:"},"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":"2407.08713","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T17:50:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"45e4dd412c4bce0bed06aaa57184a28206f28151340b58a5185941e24cc290fd","abstract_canon_sha256":"a2bd5b5447d8df2df6be8caec7e00cbc537c68a1fd2c5c2819fad8a1510ee92b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:07.839690Z","signature_b64":"f2fFuoCA3Ax3vP8iJmqmStxZWKuDnzTvdNhNORX3rTvMs1jOlrwQv0+zTvDtXbn1SDBy/lzS02xq4QeEHQEPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da8f3aa37a8d95b3663cc652e9d626ac8f2cee03f8354865d81ff55d940488dc","last_reissued_at":"2026-07-05T09:39:07.839198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:07.839198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GTA: A Benchmark for General Tool Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cailian Chen, Jize Wang, Kai Chen, Songyang Zhang, Xinyi Le, Yining Li, Zerun Ma","submitted_at":"2024-07-11T17:50:09Z","abstract_excerpt":"Significant focus has been placed on integrating large language models (LLMs) with various tools in developing general-purpose agents. This poses a challenge to LLMs' tool-use capabilities. However, there are evident gaps between existing tool-use evaluations and real-world scenarios. Current evaluations often use AI-generated queries, single-step tasks, dummy tools, and text-only interactions, failing to reveal the agents' real-world problem-solving abilities effectively. To address this, we propose GTA, a benchmark for General Tool Agents, featuring three main aspects: (i) Real user queries:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08713","kind":"arxiv","version":2},"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/2407.08713/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":"2407.08713","created_at":"2026-07-05T09:39:07.839257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08713v2","created_at":"2026-07-05T09:39:07.839257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08713","created_at":"2026-07-05T09:39:07.839257+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KHTVI32RWK3","created_at":"2026-07-05T09:39:07.839257+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KHTVI32RWK3GZR4","created_at":"2026-07-05T09:39:07.839257+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KHTVI32","created_at":"2026-07-05T09:39:07.839257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.23883","citing_title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","ref_index":235,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3KHTVI32RWK3GZR4YZJOTVRGVS","json":"https://pith.science/pith/3KHTVI32RWK3GZR4YZJOTVRGVS.json","graph_json":"https://pith.science/api/pith-number/3KHTVI32RWK3GZR4YZJOTVRGVS/graph.json","events_json":"https://pith.science/api/pith-number/3KHTVI32RWK3GZR4YZJOTVRGVS/events.json","paper":"https://pith.science/paper/3KHTVI32"},"agent_actions":{"view_html":"https://pith.science/pith/3KHTVI32RWK3GZR4YZJOTVRGVS","download_json":"https://pith.science/pith/3KHTVI32RWK3GZR4YZJOTVRGVS.json","view_paper":"https://pith.science/paper/3KHTVI32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08713&json=true","fetch_graph":"https://pith.science/api/pith-number/3KHTVI32RWK3GZR4YZJOTVRGVS/graph.json","fetch_events":"https://pith.science/api/pith-number/3KHTVI32RWK3GZR4YZJOTVRGVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KHTVI32RWK3GZR4YZJOTVRGVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KHTVI32RWK3GZR4YZJOTVRGVS/action/storage_attestation","attest_author":"https://pith.science/pith/3KHTVI32RWK3GZR4YZJOTVRGVS/action/author_attestation","sign_citation":"https://pith.science/pith/3KHTVI32RWK3GZR4YZJOTVRGVS/action/citation_signature","submit_replication":"https://pith.science/pith/3KHTVI32RWK3GZR4YZJOTVRGVS/action/replication_record"}},"created_at":"2026-07-05T09:39:07.839257+00:00","updated_at":"2026-07-05T09:39:07.839257+00:00"}