{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KMZR4RHIKNNO6WJVYLBZWLBLV6","short_pith_number":"pith:KMZR4RHI","schema_version":"1.0","canonical_sha256":"53331e44e8535aef5935c2c39b2c2bafa1c1fe27597b33408abb7c46da503546","source":{"kind":"arxiv","id":"2412.07017","version":1},"attestation_state":"computed","paper":{"title":"Asynchronous LLM Function Calling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"In Gim, Lin Zhong, Seung-seob Lee","submitted_at":"2024-12-09T21:53:10Z","abstract_excerpt":"Large language models (LLMs) use function calls to interface with external tools and data source. However, the current approach to LLM function calling is inherently synchronous, where each call blocks LLM inference, limiting LLM operation and concurrent function execution. In this work, we propose AsyncLM, a system for asynchronous LLM function calling. AsyncLM improves LLM's operational efficiency by enabling LLMs to generate and execute function calls concurrently. Instead of waiting for each call's completion, AsyncLM introduces an interrupt mechanism to asynchronously notify the LLM in-fl"},"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":"2412.07017","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T21:53:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"51add5c3e5b6efd8141182c89a8deb2f03884fa7ac69e2c77a9d09ac67679da2","abstract_canon_sha256":"36201f4cc395af86465d2b5e32ba0bd99c27c721ae404959321355ca79ebfbcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:02.179049Z","signature_b64":"o5z/89Bf+Ee7trcdl/XXc91mPK2DDLXnOp4TnhG9LXIf+WVBSt7D4BPKKqOSpRL4vqfcRDfXfCf4zOmrAMRHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53331e44e8535aef5935c2c39b2c2bafa1c1fe27597b33408abb7c46da503546","last_reissued_at":"2026-07-05T09:47:02.178489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:02.178489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asynchronous LLM Function Calling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"In Gim, Lin Zhong, Seung-seob Lee","submitted_at":"2024-12-09T21:53:10Z","abstract_excerpt":"Large language models (LLMs) use function calls to interface with external tools and data source. However, the current approach to LLM function calling is inherently synchronous, where each call blocks LLM inference, limiting LLM operation and concurrent function execution. In this work, we propose AsyncLM, a system for asynchronous LLM function calling. AsyncLM improves LLM's operational efficiency by enabling LLMs to generate and execute function calls concurrently. Instead of waiting for each call's completion, AsyncLM introduces an interrupt mechanism to asynchronously notify the LLM in-fl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07017","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/2412.07017/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":"2412.07017","created_at":"2026-07-05T09:47:02.178552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07017v1","created_at":"2026-07-05T09:47:02.178552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07017","created_at":"2026-07-05T09:47:02.178552+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMZR4RHIKNNO","created_at":"2026-07-05T09:47:02.178552+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMZR4RHIKNNO6WJV","created_at":"2026-07-05T09:47:02.178552+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMZR4RHI","created_at":"2026-07-05T09:47:02.178552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15077","citing_title":"Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22154","citing_title":"IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22733","citing_title":"HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02230","citing_title":"Continuum: Efficient and Robust Multi-Turn LLM Agent Scheduling with KV Cache Time-to-Live","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMZR4RHIKNNO6WJVYLBZWLBLV6","json":"https://pith.science/pith/KMZR4RHIKNNO6WJVYLBZWLBLV6.json","graph_json":"https://pith.science/api/pith-number/KMZR4RHIKNNO6WJVYLBZWLBLV6/graph.json","events_json":"https://pith.science/api/pith-number/KMZR4RHIKNNO6WJVYLBZWLBLV6/events.json","paper":"https://pith.science/paper/KMZR4RHI"},"agent_actions":{"view_html":"https://pith.science/pith/KMZR4RHIKNNO6WJVYLBZWLBLV6","download_json":"https://pith.science/pith/KMZR4RHIKNNO6WJVYLBZWLBLV6.json","view_paper":"https://pith.science/paper/KMZR4RHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07017&json=true","fetch_graph":"https://pith.science/api/pith-number/KMZR4RHIKNNO6WJVYLBZWLBLV6/graph.json","fetch_events":"https://pith.science/api/pith-number/KMZR4RHIKNNO6WJVYLBZWLBLV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMZR4RHIKNNO6WJVYLBZWLBLV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMZR4RHIKNNO6WJVYLBZWLBLV6/action/storage_attestation","attest_author":"https://pith.science/pith/KMZR4RHIKNNO6WJVYLBZWLBLV6/action/author_attestation","sign_citation":"https://pith.science/pith/KMZR4RHIKNNO6WJVYLBZWLBLV6/action/citation_signature","submit_replication":"https://pith.science/pith/KMZR4RHIKNNO6WJVYLBZWLBLV6/action/replication_record"}},"created_at":"2026-07-05T09:47:02.178552+00:00","updated_at":"2026-07-05T09:47:02.178552+00:00"}