{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WHWUOPCDVD5UVZY5MDFOUNZEQY","short_pith_number":"pith:WHWUOPCD","schema_version":"1.0","canonical_sha256":"b1ed473c43a8fb4ae71d60caea372486166ddbb525762172d7eca1f2c2b0f33c","source":{"kind":"arxiv","id":"2606.09613","version":1},"attestation_state":"computed","paper":{"title":"AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mengxin Zheng, Qian Lou, Rakibul Hasan Rajib","submitted_at":"2026-06-08T15:20:23Z","abstract_excerpt":"Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution. Serving these workloads requires scheduling, KV-cache management, and routing policies that use program-level context, including turn dependencies, tool-induced gaps, and reusable KV state. Evaluating such policies directly on real systems is costly, since each design point may require dedicated accelerator time across arrival rates, model scales, serving-instance counts, and memory hierarchies. Simulation offers a scalable alternative, "},"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":"2606.09613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T15:20:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de590bf02775f3325a6d3b40d4ee67974649ba9ae3b1962813aa8e08f7eb19c4","abstract_canon_sha256":"feda38b59a428ee838bfb5baec4ec75147416ae4d329b2eed3737cab751504bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:58.930797Z","signature_b64":"t1TQSdffJykOGXYTxWeAZODYwkN4USHGoHhbEqw2+xBQxXDMcXyfguw5xUuLj0hKkYCvN79Dow8uPXu5/HUuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1ed473c43a8fb4ae71d60caea372486166ddbb525762172d7eca1f2c2b0f33c","last_reissued_at":"2026-06-09T02:08:58.929833Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:58.929833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mengxin Zheng, Qian Lou, Rakibul Hasan Rajib","submitted_at":"2026-06-08T15:20:23Z","abstract_excerpt":"Multi-turn LLM agents interleave model calls with external tool invocations, shifting serving from stateless request processing to stateful program execution. Serving these workloads requires scheduling, KV-cache management, and routing policies that use program-level context, including turn dependencies, tool-induced gaps, and reusable KV state. Evaluating such policies directly on real systems is costly, since each design point may require dedicated accelerator time across arrival rates, model scales, serving-instance counts, and memory hierarchies. Simulation offers a scalable alternative, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09613","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/2606.09613/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":"2606.09613","created_at":"2026-06-09T02:08:58.929935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09613v1","created_at":"2026-06-09T02:08:58.929935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09613","created_at":"2026-06-09T02:08:58.929935+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHWUOPCDVD5U","created_at":"2026-06-09T02:08:58.929935+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHWUOPCDVD5UVZY5","created_at":"2026-06-09T02:08:58.929935+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHWUOPCD","created_at":"2026-06-09T02:08:58.929935+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/WHWUOPCDVD5UVZY5MDFOUNZEQY","json":"https://pith.science/pith/WHWUOPCDVD5UVZY5MDFOUNZEQY.json","graph_json":"https://pith.science/api/pith-number/WHWUOPCDVD5UVZY5MDFOUNZEQY/graph.json","events_json":"https://pith.science/api/pith-number/WHWUOPCDVD5UVZY5MDFOUNZEQY/events.json","paper":"https://pith.science/paper/WHWUOPCD"},"agent_actions":{"view_html":"https://pith.science/pith/WHWUOPCDVD5UVZY5MDFOUNZEQY","download_json":"https://pith.science/pith/WHWUOPCDVD5UVZY5MDFOUNZEQY.json","view_paper":"https://pith.science/paper/WHWUOPCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09613&json=true","fetch_graph":"https://pith.science/api/pith-number/WHWUOPCDVD5UVZY5MDFOUNZEQY/graph.json","fetch_events":"https://pith.science/api/pith-number/WHWUOPCDVD5UVZY5MDFOUNZEQY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHWUOPCDVD5UVZY5MDFOUNZEQY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHWUOPCDVD5UVZY5MDFOUNZEQY/action/storage_attestation","attest_author":"https://pith.science/pith/WHWUOPCDVD5UVZY5MDFOUNZEQY/action/author_attestation","sign_citation":"https://pith.science/pith/WHWUOPCDVD5UVZY5MDFOUNZEQY/action/citation_signature","submit_replication":"https://pith.science/pith/WHWUOPCDVD5UVZY5MDFOUNZEQY/action/replication_record"}},"created_at":"2026-06-09T02:08:58.929935+00:00","updated_at":"2026-06-09T02:08:58.929935+00:00"}