{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ENYZGJ4HKBFBNVRRPT4Z5PUGVK","short_pith_number":"pith:ENYZGJ4H","schema_version":"1.0","canonical_sha256":"2371932787504a16d6317cf99ebe86aabc74d0c32485b3214d5ea4d0961a46bd","source":{"kind":"arxiv","id":"2402.15960","version":2},"attestation_state":"computed","paper":{"title":"Budget-Constrained Tool Learning with Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fei Huang, Ji Zhang, Ming Yan, Peng Li, Yang Liu, Yuanhang Zheng","submitted_at":"2024-02-25T02:46:33Z","abstract_excerpt":"Despite intensive efforts devoted to tool learning, the problem of budget-constrained tool learning, which focuses on resolving user queries within a specific budget constraint, has been widely overlooked. This paper proposes a novel method for budget-constrained tool learning. Our approach involves creating a preferable plan under the budget constraint before utilizing the tools. This plan outlines the feasible tools and the maximum number of times they can be employed, offering a comprehensive overview of the tool learning process for large language models. This allows them to allocate the b"},"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":"2402.15960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-25T02:46:33Z","cross_cats_sorted":[],"title_canon_sha256":"49322509c51ca93a3b35d442895a7a71ad467ca7ce595a84e577567752078a44","abstract_canon_sha256":"81caf1cb86710dc4b6eaded47400b821beaa941281780d0ccf24ac4825c6a6e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:45.962271Z","signature_b64":"m2t76V+iq34pj8nKjdo8yM2PhdpeILEY1G5IkaXnOPVxFj1NiEGvQgNTEZgnbwnB1YNRn3snMhOB7oMlMzzVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2371932787504a16d6317cf99ebe86aabc74d0c32485b3214d5ea4d0961a46bd","last_reissued_at":"2026-07-05T08:29:45.961764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:45.961764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Budget-Constrained Tool Learning with Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fei Huang, Ji Zhang, Ming Yan, Peng Li, Yang Liu, Yuanhang Zheng","submitted_at":"2024-02-25T02:46:33Z","abstract_excerpt":"Despite intensive efforts devoted to tool learning, the problem of budget-constrained tool learning, which focuses on resolving user queries within a specific budget constraint, has been widely overlooked. This paper proposes a novel method for budget-constrained tool learning. Our approach involves creating a preferable plan under the budget constraint before utilizing the tools. This plan outlines the feasible tools and the maximum number of times they can be employed, offering a comprehensive overview of the tool learning process for large language models. This allows them to allocate the b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15960","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/2402.15960/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":"2402.15960","created_at":"2026-07-05T08:29:45.961827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15960v2","created_at":"2026-07-05T08:29:45.961827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15960","created_at":"2026-07-05T08:29:45.961827+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENYZGJ4HKBFB","created_at":"2026-07-05T08:29:45.961827+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENYZGJ4HKBFBNVRR","created_at":"2026-07-05T08:29:45.961827+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENYZGJ4H","created_at":"2026-07-05T08:29:45.961827+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/ENYZGJ4HKBFBNVRRPT4Z5PUGVK","json":"https://pith.science/pith/ENYZGJ4HKBFBNVRRPT4Z5PUGVK.json","graph_json":"https://pith.science/api/pith-number/ENYZGJ4HKBFBNVRRPT4Z5PUGVK/graph.json","events_json":"https://pith.science/api/pith-number/ENYZGJ4HKBFBNVRRPT4Z5PUGVK/events.json","paper":"https://pith.science/paper/ENYZGJ4H"},"agent_actions":{"view_html":"https://pith.science/pith/ENYZGJ4HKBFBNVRRPT4Z5PUGVK","download_json":"https://pith.science/pith/ENYZGJ4HKBFBNVRRPT4Z5PUGVK.json","view_paper":"https://pith.science/paper/ENYZGJ4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15960&json=true","fetch_graph":"https://pith.science/api/pith-number/ENYZGJ4HKBFBNVRRPT4Z5PUGVK/graph.json","fetch_events":"https://pith.science/api/pith-number/ENYZGJ4HKBFBNVRRPT4Z5PUGVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENYZGJ4HKBFBNVRRPT4Z5PUGVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENYZGJ4HKBFBNVRRPT4Z5PUGVK/action/storage_attestation","attest_author":"https://pith.science/pith/ENYZGJ4HKBFBNVRRPT4Z5PUGVK/action/author_attestation","sign_citation":"https://pith.science/pith/ENYZGJ4HKBFBNVRRPT4Z5PUGVK/action/citation_signature","submit_replication":"https://pith.science/pith/ENYZGJ4HKBFBNVRRPT4Z5PUGVK/action/replication_record"}},"created_at":"2026-07-05T08:29:45.961827+00:00","updated_at":"2026-07-05T08:29:45.961827+00:00"}