{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KDMUTZSEFEUH5XLF3XHVVSDRAY","short_pith_number":"pith:KDMUTZSE","schema_version":"1.0","canonical_sha256":"50d949e64429287edd65ddcf5ac87106076e37b64b14c11aa7ac759400ff56c1","source":{"kind":"arxiv","id":"2410.03212","version":1},"attestation_state":"computed","paper":{"title":"Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chongxian Chen, Fan Mo, Hayato Yamana, Junjie Wang, Tetsuya Sakai, Xin Fan, Yuxiang Zhang","submitted_at":"2024-10-04T07:58:05Z","abstract_excerpt":"Recent advancements in large language models (LLMs) integrated with external tools and APIs have successfully addressed complex tasks by using in-context learning or fine-tuning. Despite this progress, the vast scale of tool retrieval remains challenging due to stringent input length constraints. In response, we propose a pre-retrieval strategy from an extensive repository, effectively framing the problem as the massive tool retrieval (MTR) task. We introduce the MTRB (massive tool retrieval benchmark) to evaluate real-world tool-augmented LLM scenarios with a large number of tools. This bench"},"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":"2410.03212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-10-04T07:58:05Z","cross_cats_sorted":[],"title_canon_sha256":"e5841438dc241fcbdad8eca3a269c3a9594cc62dbf4521e72067445fad674fc2","abstract_canon_sha256":"dc0f2ceddd18e8bc3c996ab995ea072ea05c16e407f768bb7627819c83c89dba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:46.296993Z","signature_b64":"wqRg1/VJSvbsYxsGcO3SY0LuKZfzj0nxVZSEw3M3DlBLD4gEByQnoxs7x8Qo2folZAJc0AdjxFvHcLIcuuB9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d949e64429287edd65ddcf5ac87106076e37b64b14c11aa7ac759400ff56c1","last_reissued_at":"2026-07-05T09:15:46.296622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:46.296622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Massive Tool Retrieval: A Reinforcement Learning Approach for Query-Tool Alignment with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chongxian Chen, Fan Mo, Hayato Yamana, Junjie Wang, Tetsuya Sakai, Xin Fan, Yuxiang Zhang","submitted_at":"2024-10-04T07:58:05Z","abstract_excerpt":"Recent advancements in large language models (LLMs) integrated with external tools and APIs have successfully addressed complex tasks by using in-context learning or fine-tuning. Despite this progress, the vast scale of tool retrieval remains challenging due to stringent input length constraints. In response, we propose a pre-retrieval strategy from an extensive repository, effectively framing the problem as the massive tool retrieval (MTR) task. We introduce the MTRB (massive tool retrieval benchmark) to evaluate real-world tool-augmented LLM scenarios with a large number of tools. This bench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03212","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/2410.03212/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":"2410.03212","created_at":"2026-07-05T09:15:46.296684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03212v1","created_at":"2026-07-05T09:15:46.296684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03212","created_at":"2026-07-05T09:15:46.296684+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDMUTZSEFEUH","created_at":"2026-07-05T09:15:46.296684+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDMUTZSEFEUH5XLF","created_at":"2026-07-05T09:15:46.296684+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDMUTZSE","created_at":"2026-07-05T09:15:46.296684+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDMUTZSEFEUH5XLF3XHVVSDRAY","json":"https://pith.science/pith/KDMUTZSEFEUH5XLF3XHVVSDRAY.json","graph_json":"https://pith.science/api/pith-number/KDMUTZSEFEUH5XLF3XHVVSDRAY/graph.json","events_json":"https://pith.science/api/pith-number/KDMUTZSEFEUH5XLF3XHVVSDRAY/events.json","paper":"https://pith.science/paper/KDMUTZSE"},"agent_actions":{"view_html":"https://pith.science/pith/KDMUTZSEFEUH5XLF3XHVVSDRAY","download_json":"https://pith.science/pith/KDMUTZSEFEUH5XLF3XHVVSDRAY.json","view_paper":"https://pith.science/paper/KDMUTZSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03212&json=true","fetch_graph":"https://pith.science/api/pith-number/KDMUTZSEFEUH5XLF3XHVVSDRAY/graph.json","fetch_events":"https://pith.science/api/pith-number/KDMUTZSEFEUH5XLF3XHVVSDRAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDMUTZSEFEUH5XLF3XHVVSDRAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDMUTZSEFEUH5XLF3XHVVSDRAY/action/storage_attestation","attest_author":"https://pith.science/pith/KDMUTZSEFEUH5XLF3XHVVSDRAY/action/author_attestation","sign_citation":"https://pith.science/pith/KDMUTZSEFEUH5XLF3XHVVSDRAY/action/citation_signature","submit_replication":"https://pith.science/pith/KDMUTZSEFEUH5XLF3XHVVSDRAY/action/replication_record"}},"created_at":"2026-07-05T09:15:46.296684+00:00","updated_at":"2026-07-05T09:15:46.296684+00:00"}