{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J2R3L3DETKTLLXMZCCCR4Z2JSH","short_pith_number":"pith:J2R3L3DE","schema_version":"1.0","canonical_sha256":"4ea3b5ec649aa6b5dd9910851e674991fe67204e8eb095557f74fccb7f562568","source":{"kind":"arxiv","id":"2406.00059","version":2},"attestation_state":"computed","paper":{"title":"Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Danyang Zhuo, Tingjun Chen, Xinhao Kong, Yechen Xu","submitted_at":"2024-05-29T21:24:15Z","abstract_excerpt":"The complexity of large language model (LLM) serving workloads has substantially increased due to the integration with external tool invocations, such as ChatGPT plugins. In this paper, we identify a new opportunity for efficient LLM serving for requests that trigger tools: tool partial execution alongside LLM decoding. To this end, we design Conveyor, an efficient LLM serving system optimized for handling requests involving external tools. We introduce a novel interface for tool developers to expose partial execution opportunities to the LLM serving system and a request scheduler that facilit"},"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":"2406.00059","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T21:24:15Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"df4c6ba0ad3240bb1cdd5d8376e5481b47a9b3a631189ce16a9c51128f933d89","abstract_canon_sha256":"d8d055a84957ca48f5c1483f8d6bb830453b0b6900513ed4f50698840f9ca145"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:26.381814Z","signature_b64":"WMSipagiyoNO89qrV9k8WvlI6yAN6aj4CFMQ/DOFjQq2EexWg6bnOp1IYhAsWsji/RQpISpUfPMF9yxiy5XLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ea3b5ec649aa6b5dd9910851e674991fe67204e8eb095557f74fccb7f562568","last_reissued_at":"2026-07-05T08:27:26.381358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:26.381358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conveyor: Efficient Tool-aware LLM Serving with Tool Partial Execution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Danyang Zhuo, Tingjun Chen, Xinhao Kong, Yechen Xu","submitted_at":"2024-05-29T21:24:15Z","abstract_excerpt":"The complexity of large language model (LLM) serving workloads has substantially increased due to the integration with external tool invocations, such as ChatGPT plugins. In this paper, we identify a new opportunity for efficient LLM serving for requests that trigger tools: tool partial execution alongside LLM decoding. To this end, we design Conveyor, an efficient LLM serving system optimized for handling requests involving external tools. We introduce a novel interface for tool developers to expose partial execution opportunities to the LLM serving system and a request scheduler that facilit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00059","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/2406.00059/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":"2406.00059","created_at":"2026-07-05T08:27:26.381416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00059v2","created_at":"2026-07-05T08:27:26.381416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00059","created_at":"2026-07-05T08:27:26.381416+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2R3L3DETKTL","created_at":"2026-07-05T08:27:26.381416+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2R3L3DETKTLLXMZ","created_at":"2026-07-05T08:27:26.381416+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2R3L3DE","created_at":"2026-07-05T08:27:26.381416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.00739","citing_title":"Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2R3L3DETKTLLXMZCCCR4Z2JSH","json":"https://pith.science/pith/J2R3L3DETKTLLXMZCCCR4Z2JSH.json","graph_json":"https://pith.science/api/pith-number/J2R3L3DETKTLLXMZCCCR4Z2JSH/graph.json","events_json":"https://pith.science/api/pith-number/J2R3L3DETKTLLXMZCCCR4Z2JSH/events.json","paper":"https://pith.science/paper/J2R3L3DE"},"agent_actions":{"view_html":"https://pith.science/pith/J2R3L3DETKTLLXMZCCCR4Z2JSH","download_json":"https://pith.science/pith/J2R3L3DETKTLLXMZCCCR4Z2JSH.json","view_paper":"https://pith.science/paper/J2R3L3DE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00059&json=true","fetch_graph":"https://pith.science/api/pith-number/J2R3L3DETKTLLXMZCCCR4Z2JSH/graph.json","fetch_events":"https://pith.science/api/pith-number/J2R3L3DETKTLLXMZCCCR4Z2JSH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2R3L3DETKTLLXMZCCCR4Z2JSH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2R3L3DETKTLLXMZCCCR4Z2JSH/action/storage_attestation","attest_author":"https://pith.science/pith/J2R3L3DETKTLLXMZCCCR4Z2JSH/action/author_attestation","sign_citation":"https://pith.science/pith/J2R3L3DETKTLLXMZCCCR4Z2JSH/action/citation_signature","submit_replication":"https://pith.science/pith/J2R3L3DETKTLLXMZCCCR4Z2JSH/action/replication_record"}},"created_at":"2026-07-05T08:27:26.381416+00:00","updated_at":"2026-07-05T08:27:26.381416+00:00"}