{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KMLEVUUGVVSNN4Z6WFBDJ7LFDH","short_pith_number":"pith:KMLEVUUG","schema_version":"1.0","canonical_sha256":"53164ad286ad64d6f33eb14234fd6519c104d0fe42e60e4fecd1dd4b9807afc9","source":{"kind":"arxiv","id":"2503.01763","version":2},"attestation_state":"computed","paper":{"title":"Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Yuhan Wang, Zhaochun Ren, Zhengliang Shi","submitted_at":"2025-03-03T17:37:16Z","abstract_excerpt":"Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks. Due to the limited context length of tool-using LLMs, adopting information retrieval (IR) models to select useful tools from large toolsets is a critical initial step. However, the performance of IR models in tool retrieval tasks remains underexplored and unclear. Most tool-use benchmarks simplify this step by manually pre-annotating a small set of relevant tools for each task, which is far from the real-world scenarios. In this paper, we propose ToolRet, a"},"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":"2503.01763","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T17:37:16Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"e787c5daecac2c69c51923a34f7d6ffd67b914d6da7188b4088e9b819585fd51","abstract_canon_sha256":"720fbfedf6b0c89ff295e8949ab3efa55f1b1541b386a30a5845d9e81f2456b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:45.767364Z","signature_b64":"foRmAZ+n5THEJWXYUJNip/oKMEFdjmGoUEa9uutPQ2pvLwwm3k413QykCo3OyHcbXQXMQyWpaULw4Oh5ftY4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53164ad286ad64d6f33eb14234fd6519c104d0fe42e60e4fecd1dd4b9807afc9","last_reissued_at":"2026-07-05T11:09:45.766865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:45.766865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Yuhan Wang, Zhaochun Ren, Zhengliang Shi","submitted_at":"2025-03-03T17:37:16Z","abstract_excerpt":"Tool learning aims to augment large language models (LLMs) with diverse tools, enabling them to act as agents for solving practical tasks. Due to the limited context length of tool-using LLMs, adopting information retrieval (IR) models to select useful tools from large toolsets is a critical initial step. However, the performance of IR models in tool retrieval tasks remains underexplored and unclear. Most tool-use benchmarks simplify this step by manually pre-annotating a small set of relevant tools for each task, which is far from the real-world scenarios. In this paper, we propose ToolRet, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01763","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/2503.01763/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":"2503.01763","created_at":"2026-07-05T11:09:45.766925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01763v2","created_at":"2026-07-05T11:09:45.766925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01763","created_at":"2026-07-05T11:09:45.766925+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMLEVUUGVVSN","created_at":"2026-07-05T11:09:45.766925+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMLEVUUGVVSNN4Z6","created_at":"2026-07-05T11:09:45.766925+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMLEVUUG","created_at":"2026-07-05T11:09:45.766925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07904","citing_title":"Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03056","citing_title":"SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05726","citing_title":"SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22820","citing_title":"Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMLEVUUGVVSNN4Z6WFBDJ7LFDH","json":"https://pith.science/pith/KMLEVUUGVVSNN4Z6WFBDJ7LFDH.json","graph_json":"https://pith.science/api/pith-number/KMLEVUUGVVSNN4Z6WFBDJ7LFDH/graph.json","events_json":"https://pith.science/api/pith-number/KMLEVUUGVVSNN4Z6WFBDJ7LFDH/events.json","paper":"https://pith.science/paper/KMLEVUUG"},"agent_actions":{"view_html":"https://pith.science/pith/KMLEVUUGVVSNN4Z6WFBDJ7LFDH","download_json":"https://pith.science/pith/KMLEVUUGVVSNN4Z6WFBDJ7LFDH.json","view_paper":"https://pith.science/paper/KMLEVUUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01763&json=true","fetch_graph":"https://pith.science/api/pith-number/KMLEVUUGVVSNN4Z6WFBDJ7LFDH/graph.json","fetch_events":"https://pith.science/api/pith-number/KMLEVUUGVVSNN4Z6WFBDJ7LFDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMLEVUUGVVSNN4Z6WFBDJ7LFDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMLEVUUGVVSNN4Z6WFBDJ7LFDH/action/storage_attestation","attest_author":"https://pith.science/pith/KMLEVUUGVVSNN4Z6WFBDJ7LFDH/action/author_attestation","sign_citation":"https://pith.science/pith/KMLEVUUGVVSNN4Z6WFBDJ7LFDH/action/citation_signature","submit_replication":"https://pith.science/pith/KMLEVUUGVVSNN4Z6WFBDJ7LFDH/action/replication_record"}},"created_at":"2026-07-05T11:09:45.766925+00:00","updated_at":"2026-07-05T11:09:45.766925+00:00"}