{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F5QGCFW5UYJBVTH3AUCW5T3KSL","short_pith_number":"pith:F5QGCFW5","schema_version":"1.0","canonical_sha256":"2f606116dda6121accfb05056ecf6a92f0b8a334088b917a30c77c39753ea45e","source":{"kind":"arxiv","id":"2606.03014","version":1},"attestation_state":"computed","paper":{"title":"MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Nazmul Takbir, Phyo Pyae Moe Aung, Rachid Karami, Saptarshi Mitra, Sitao Huang, Souvik Kundu, Sreetama Sarkar, Yifan Zhang","submitted_at":"2026-06-02T01:40:33Z","abstract_excerpt":"Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently executing this workload on limited GPU resources has bottlenecks. Skill-based routing creates skewed expert demand, and combining instruction-tuned LLMs with long-reasoning models results in extreme variability in generation lengths. Consequently, traditional scheduling strategies suffer from significant GPU idling and throughput collapse due to load imbalances. We present MOSAIC, a scheduling framework to accelerate MoA workloads. First, we formul"},"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":"2606.03014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T01:40:33Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"d39e39fd94001a12ad20c4fcc54ab752a0a5edb636e47bdb80357b2562c4ed3b","abstract_canon_sha256":"f9349652a18020a066c5144764c59c4411c6244c465a69ef60225e8b6e744e11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:29.282066Z","signature_b64":"CSBV/BbDfi1E+D7ENQduVC/bSGC2ZEalm0hv767xMy4OJbr2mNbnFzvZh5aKxIPJr6OS5Z7EZsKyrpfcIHGTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f606116dda6121accfb05056ecf6a92f0b8a334088b917a30c77c39753ea45e","last_reissued_at":"2026-06-03T01:05:29.281640Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:29.281640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Nazmul Takbir, Phyo Pyae Moe Aung, Rachid Karami, Saptarshi Mitra, Sitao Huang, Souvik Kundu, Sreetama Sarkar, Yifan Zhang","submitted_at":"2026-06-02T01:40:33Z","abstract_excerpt":"Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently executing this workload on limited GPU resources has bottlenecks. Skill-based routing creates skewed expert demand, and combining instruction-tuned LLMs with long-reasoning models results in extreme variability in generation lengths. Consequently, traditional scheduling strategies suffer from significant GPU idling and throughput collapse due to load imbalances. We present MOSAIC, a scheduling framework to accelerate MoA workloads. First, we formul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03014","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/2606.03014/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":"2606.03014","created_at":"2026-06-03T01:05:29.281700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03014v1","created_at":"2026-06-03T01:05:29.281700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03014","created_at":"2026-06-03T01:05:29.281700+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5QGCFW5UYJB","created_at":"2026-06-03T01:05:29.281700+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5QGCFW5UYJBVTH3","created_at":"2026-06-03T01:05:29.281700+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5QGCFW5","created_at":"2026-06-03T01:05:29.281700+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/F5QGCFW5UYJBVTH3AUCW5T3KSL","json":"https://pith.science/pith/F5QGCFW5UYJBVTH3AUCW5T3KSL.json","graph_json":"https://pith.science/api/pith-number/F5QGCFW5UYJBVTH3AUCW5T3KSL/graph.json","events_json":"https://pith.science/api/pith-number/F5QGCFW5UYJBVTH3AUCW5T3KSL/events.json","paper":"https://pith.science/paper/F5QGCFW5"},"agent_actions":{"view_html":"https://pith.science/pith/F5QGCFW5UYJBVTH3AUCW5T3KSL","download_json":"https://pith.science/pith/F5QGCFW5UYJBVTH3AUCW5T3KSL.json","view_paper":"https://pith.science/paper/F5QGCFW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03014&json=true","fetch_graph":"https://pith.science/api/pith-number/F5QGCFW5UYJBVTH3AUCW5T3KSL/graph.json","fetch_events":"https://pith.science/api/pith-number/F5QGCFW5UYJBVTH3AUCW5T3KSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5QGCFW5UYJBVTH3AUCW5T3KSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5QGCFW5UYJBVTH3AUCW5T3KSL/action/storage_attestation","attest_author":"https://pith.science/pith/F5QGCFW5UYJBVTH3AUCW5T3KSL/action/author_attestation","sign_citation":"https://pith.science/pith/F5QGCFW5UYJBVTH3AUCW5T3KSL/action/citation_signature","submit_replication":"https://pith.science/pith/F5QGCFW5UYJBVTH3AUCW5T3KSL/action/replication_record"}},"created_at":"2026-06-03T01:05:29.281700+00:00","updated_at":"2026-06-03T01:05:29.281700+00:00"}