{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RXESL2GFGREJ5PRJZLNR2TC3NV","short_pith_number":"pith:RXESL2GF","schema_version":"1.0","canonical_sha256":"8dc925e8c534489ebe29cadb1d4c5b6d47cf630d5469798d528211472ce81600","source":{"kind":"arxiv","id":"2410.11710","version":1},"attestation_state":"computed","paper":{"title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Chenchen Zhang, Ge Zhang, Hangyu Guo, Jiaheng Liu, Jiakai Wang, Junran Peng, Ken Deng, Pei Wang, Wenbo Su, Xiaoshuai Song, Yanan Wu, Zekun Wang, Zhaoxiang Zhang, Zhongyuan Peng","submitted_at":"2024-10-15T15:46:17Z","abstract_excerpt":"Large Language Models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Recently, many tool-use benchmark datasets have been proposed. However, existing datasets have the following limitations: (1). Insufficient evaluation scenarios (e.g., only cover limited tool-use scenes). (2). Extensive evaluation costs (e.g., GPT API costs). To address these limitations, in this work, we propose a multi-granularity tool-use benchmark for large language models called MTU-Bench. For the \"multi-granularity\" property, our MTU-Benc"},"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":"2410.11710","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T15:46:17Z","cross_cats_sorted":[],"title_canon_sha256":"9b142fd439bca6b59c9bfc13020d3237c783f70c8d6157bf6b9605a2c53c5e75","abstract_canon_sha256":"64016ae8832331a9af4ca30310a90fffe824f9d1a690cca14cfd787f0cebadc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:57.967776Z","signature_b64":"gka+PANjJ+X7DTdFhILo8pc9Yqt9Tlzk6wgRYPRoWXqiMeMKYEYucEhF1yUaj/SksJK9+Ajxbfuk5WbimfGMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc925e8c534489ebe29cadb1d4c5b6d47cf630d5469798d528211472ce81600","last_reissued_at":"2026-07-05T09:20:57.967376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:57.967376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zheng, Chenchen Zhang, Ge Zhang, Hangyu Guo, Jiaheng Liu, Jiakai Wang, Junran Peng, Ken Deng, Pei Wang, Wenbo Su, Xiaoshuai Song, Yanan Wu, Zekun Wang, Zhaoxiang Zhang, Zhongyuan Peng","submitted_at":"2024-10-15T15:46:17Z","abstract_excerpt":"Large Language Models (LLMs) have displayed massive improvements in reasoning and decision-making skills and can hold natural conversations with users. Recently, many tool-use benchmark datasets have been proposed. However, existing datasets have the following limitations: (1). Insufficient evaluation scenarios (e.g., only cover limited tool-use scenes). (2). Extensive evaluation costs (e.g., GPT API costs). To address these limitations, in this work, we propose a multi-granularity tool-use benchmark for large language models called MTU-Bench. For the \"multi-granularity\" property, our MTU-Benc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11710","kind":"arxiv","version":1},"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/2410.11710/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":"2410.11710","created_at":"2026-07-05T09:20:57.967444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11710v1","created_at":"2026-07-05T09:20:57.967444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11710","created_at":"2026-07-05T09:20:57.967444+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXESL2GFGREJ","created_at":"2026-07-05T09:20:57.967444+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXESL2GFGREJ5PRJ","created_at":"2026-07-05T09:20:57.967444+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXESL2GF","created_at":"2026-07-05T09:20:57.967444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15296","citing_title":"Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXESL2GFGREJ5PRJZLNR2TC3NV","json":"https://pith.science/pith/RXESL2GFGREJ5PRJZLNR2TC3NV.json","graph_json":"https://pith.science/api/pith-number/RXESL2GFGREJ5PRJZLNR2TC3NV/graph.json","events_json":"https://pith.science/api/pith-number/RXESL2GFGREJ5PRJZLNR2TC3NV/events.json","paper":"https://pith.science/paper/RXESL2GF"},"agent_actions":{"view_html":"https://pith.science/pith/RXESL2GFGREJ5PRJZLNR2TC3NV","download_json":"https://pith.science/pith/RXESL2GFGREJ5PRJZLNR2TC3NV.json","view_paper":"https://pith.science/paper/RXESL2GF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11710&json=true","fetch_graph":"https://pith.science/api/pith-number/RXESL2GFGREJ5PRJZLNR2TC3NV/graph.json","fetch_events":"https://pith.science/api/pith-number/RXESL2GFGREJ5PRJZLNR2TC3NV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXESL2GFGREJ5PRJZLNR2TC3NV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXESL2GFGREJ5PRJZLNR2TC3NV/action/storage_attestation","attest_author":"https://pith.science/pith/RXESL2GFGREJ5PRJZLNR2TC3NV/action/author_attestation","sign_citation":"https://pith.science/pith/RXESL2GFGREJ5PRJZLNR2TC3NV/action/citation_signature","submit_replication":"https://pith.science/pith/RXESL2GFGREJ5PRJZLNR2TC3NV/action/replication_record"}},"created_at":"2026-07-05T09:20:57.967444+00:00","updated_at":"2026-07-05T09:20:57.967444+00:00"}