{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MKXCA3D256TJB2LBBKT7FBCWMZ","short_pith_number":"pith:MKXCA3D2","schema_version":"1.0","canonical_sha256":"62ae206c7aefa690e9610aa7f28456666aea378fb4fe99111af9b274e2a86b9d","source":{"kind":"arxiv","id":"2607.08565","version":1},"attestation_state":"computed","paper":{"title":"SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Chenguang Fang, Haibo Chen, Jiahao Wang, Jinbo Han, Kaixi Zhang, Kaizhan Lin, Rong chen, Sijie Shen, Wenyuan Yu, Xingda Wei","submitted_at":"2026-07-09T14:55:02Z","abstract_excerpt":"LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instead of humans. This shifts the workload in two ways: (1) agents act only on complete responses, making the cluster's tokens per second (TPS) the primary goal and relaxing--not eliminating--per-token latency requirements; and (2) requests share much of their KV\\$-reuse exceeds 80% of request tokens in a production trace from BAILIAN, versus 54-62% in chat.\n  This paper first contributes a systematic study of request scheduling for agents on two real"},"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":"2607.08565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-09T14:55:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff680bd08096292d0d95a31f17e9ffafa6c1e037902b7e90ef06e27621ebfe59","abstract_canon_sha256":"9cbc3db9f3196aa5a63b2f02e2101eff9bbe0d7fc875ac6f8447fb3ce46f8ef2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:53.789336Z","signature_b64":"oZKivGSBRqvotx7HVbOVXt1twvCClztnyqn/8rNHH/wy8zweRhbx327kIBZsS8PYvAzXs+6UmtsiYx2p7oI1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62ae206c7aefa690e9610aa7f28456666aea378fb4fe99111af9b274e2a86b9d","last_reissued_at":"2026-07-10T01:19:53.788921Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:53.788921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Chenguang Fang, Haibo Chen, Jiahao Wang, Jinbo Han, Kaixi Zhang, Kaizhan Lin, Rong chen, Sijie Shen, Wenyuan Yu, Xingda Wei","submitted_at":"2026-07-09T14:55:02Z","abstract_excerpt":"LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instead of humans. This shifts the workload in two ways: (1) agents act only on complete responses, making the cluster's tokens per second (TPS) the primary goal and relaxing--not eliminating--per-token latency requirements; and (2) requests share much of their KV\\$-reuse exceeds 80% of request tokens in a production trace from BAILIAN, versus 54-62% in chat.\n  This paper first contributes a systematic study of request scheduling for agents on two real"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08565","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/2607.08565/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":"2607.08565","created_at":"2026-07-10T01:19:53.788979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08565v1","created_at":"2026-07-10T01:19:53.788979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08565","created_at":"2026-07-10T01:19:53.788979+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKXCA3D256TJ","created_at":"2026-07-10T01:19:53.788979+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKXCA3D256TJB2LB","created_at":"2026-07-10T01:19:53.788979+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKXCA3D2","created_at":"2026-07-10T01:19:53.788979+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/MKXCA3D256TJB2LBBKT7FBCWMZ","json":"https://pith.science/pith/MKXCA3D256TJB2LBBKT7FBCWMZ.json","graph_json":"https://pith.science/api/pith-number/MKXCA3D256TJB2LBBKT7FBCWMZ/graph.json","events_json":"https://pith.science/api/pith-number/MKXCA3D256TJB2LBBKT7FBCWMZ/events.json","paper":"https://pith.science/paper/MKXCA3D2"},"agent_actions":{"view_html":"https://pith.science/pith/MKXCA3D256TJB2LBBKT7FBCWMZ","download_json":"https://pith.science/pith/MKXCA3D256TJB2LBBKT7FBCWMZ.json","view_paper":"https://pith.science/paper/MKXCA3D2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08565&json=true","fetch_graph":"https://pith.science/api/pith-number/MKXCA3D256TJB2LBBKT7FBCWMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MKXCA3D256TJB2LBBKT7FBCWMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKXCA3D256TJB2LBBKT7FBCWMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKXCA3D256TJB2LBBKT7FBCWMZ/action/storage_attestation","attest_author":"https://pith.science/pith/MKXCA3D256TJB2LBBKT7FBCWMZ/action/author_attestation","sign_citation":"https://pith.science/pith/MKXCA3D256TJB2LBBKT7FBCWMZ/action/citation_signature","submit_replication":"https://pith.science/pith/MKXCA3D256TJB2LBBKT7FBCWMZ/action/replication_record"}},"created_at":"2026-07-10T01:19:53.788979+00:00","updated_at":"2026-07-10T01:19:53.788979+00:00"}