{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UNRPMQSOOCFR6FMETS5WXKCS3W","short_pith_number":"pith:UNRPMQSO","schema_version":"1.0","canonical_sha256":"a362f6424e708b1f15849cbb6ba852dda77e0f7245753c2d7f9defa567cbb4ae","source":{"kind":"arxiv","id":"2402.04253","version":1},"attestation_state":"computed","paper":{"title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangyun Wei, Hongyang Zhang, Yu Du","submitted_at":"2024-02-06T18:59:57Z","abstract_excerpt":"We introduce AnyTool, a large language model agent designed to revolutionize the utilization of a vast array of tools in addressing user queries. We utilize over 16,000 APIs from Rapid API, operating under the assumption that a subset of these APIs could potentially resolve the queries. AnyTool primarily incorporates three elements: an API retriever with a hierarchical structure, a solver aimed at resolving user queries using a selected set of API candidates, and a self-reflection mechanism, which re-activates AnyTool if the initial solution proves impracticable. AnyTool is powered by the func"},"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":"2402.04253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T18:59:57Z","cross_cats_sorted":[],"title_canon_sha256":"7ac6c59d81bb987e95633d50a5271c86ac938208031bb9d6d7efac4e4169b263","abstract_canon_sha256":"2f2a9c13a12f61e701c14e7ad7cd78f234ba08ec1ac1f71df8afa751072251bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:05.449852Z","signature_b64":"LhoxyaFva4MgNdOqK4IbE2XwAFlNUshwNPjHsY3CG/7BJre7TA4H7k1djf+ZzFCzUluWOep2atdRHigzQEeBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a362f6424e708b1f15849cbb6ba852dda77e0f7245753c2d7f9defa567cbb4ae","last_reissued_at":"2026-07-05T07:42:05.449328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:05.449328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fangyun Wei, Hongyang Zhang, Yu Du","submitted_at":"2024-02-06T18:59:57Z","abstract_excerpt":"We introduce AnyTool, a large language model agent designed to revolutionize the utilization of a vast array of tools in addressing user queries. We utilize over 16,000 APIs from Rapid API, operating under the assumption that a subset of these APIs could potentially resolve the queries. AnyTool primarily incorporates three elements: an API retriever with a hierarchical structure, a solver aimed at resolving user queries using a selected set of API candidates, and a self-reflection mechanism, which re-activates AnyTool if the initial solution proves impracticable. AnyTool is powered by the func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04253","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/2402.04253/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":"2402.04253","created_at":"2026-07-05T07:42:05.449397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04253v1","created_at":"2026-07-05T07:42:05.449397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04253","created_at":"2026-07-05T07:42:05.449397+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNRPMQSOOCFR","created_at":"2026-07-05T07:42:05.449397+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNRPMQSOOCFR6FME","created_at":"2026-07-05T07:42:05.449397+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNRPMQSO","created_at":"2026-07-05T07:42:05.449397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18051","citing_title":"Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00251","citing_title":"Capability Self-Assessment: Teaching LLMs to Know Their Limits","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22177","citing_title":"Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10787","citing_title":"ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16508","citing_title":"The Scaling Laws of Skills in LLM Agent Systems","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":192,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19793","citing_title":"Prompt Injection Attack to Tool Selection in LLM Agents","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13391","citing_title":"RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10787","citing_title":"ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04777","citing_title":"Bridging Perception and Action: A Lightweight Multimodal Meta-Planner Framework for Robust Earth Observation Agents","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNRPMQSOOCFR6FMETS5WXKCS3W","json":"https://pith.science/pith/UNRPMQSOOCFR6FMETS5WXKCS3W.json","graph_json":"https://pith.science/api/pith-number/UNRPMQSOOCFR6FMETS5WXKCS3W/graph.json","events_json":"https://pith.science/api/pith-number/UNRPMQSOOCFR6FMETS5WXKCS3W/events.json","paper":"https://pith.science/paper/UNRPMQSO"},"agent_actions":{"view_html":"https://pith.science/pith/UNRPMQSOOCFR6FMETS5WXKCS3W","download_json":"https://pith.science/pith/UNRPMQSOOCFR6FMETS5WXKCS3W.json","view_paper":"https://pith.science/paper/UNRPMQSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04253&json=true","fetch_graph":"https://pith.science/api/pith-number/UNRPMQSOOCFR6FMETS5WXKCS3W/graph.json","fetch_events":"https://pith.science/api/pith-number/UNRPMQSOOCFR6FMETS5WXKCS3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNRPMQSOOCFR6FMETS5WXKCS3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNRPMQSOOCFR6FMETS5WXKCS3W/action/storage_attestation","attest_author":"https://pith.science/pith/UNRPMQSOOCFR6FMETS5WXKCS3W/action/author_attestation","sign_citation":"https://pith.science/pith/UNRPMQSOOCFR6FMETS5WXKCS3W/action/citation_signature","submit_replication":"https://pith.science/pith/UNRPMQSOOCFR6FMETS5WXKCS3W/action/replication_record"}},"created_at":"2026-07-05T07:42:05.449397+00:00","updated_at":"2026-07-05T07:42:05.449397+00:00"}