{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SJLDYYFWNKYH73Z7AWMUYPTOBL","short_pith_number":"pith:SJLDYYFW","schema_version":"1.0","canonical_sha256":"92563c60b66ab07fef3f05994c3e6e0ae627a89efbd16b00ec791fccc9f9ece4","source":{"kind":"arxiv","id":"2502.11133","version":1},"attestation_state":"computed","paper":{"title":"MasRouter: Learning to Route LLMs for Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Boyang Liu, Dawei Cheng, Guancheng Wan, Guibin Zhang, Kun Wang, Yanwei Yue, Yiyan Qi","submitted_at":"2025-02-16T14:00:59Z","abstract_excerpt":"Multi-agent systems (MAS) powered by Large Language Models (LLMs) have been demonstrated to push the boundaries of LLM capabilities, yet they often incur significant costs and face challenges in dynamic LLM selection. Current LLM routing methods effectively reduce overhead in single-agent scenarios by customizing LLM selection for each query, but they overlook the critical decisions regarding collaboration modes and agent roles in MAS. In response to this challenge, we first introduce the problem of Multi-Agent System Routing (MASR), which integrates all components of MAS into a unified routin"},"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":"2502.11133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-16T14:00:59Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"54c00591d1b948952272b7877e3119866913d286b84686c1fe9a6c229e9777ae","abstract_canon_sha256":"4332b9a1f68725c549e7ded754bd30272e8e26e94ff46ad929e8f11e1a6e336d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:04.237331Z","signature_b64":"hLAHYEYbM9n5k1b4AV9aeHJz/hhB4z8CLhVrUrUScKsdPKuQc7FLVtUdpmkegLkKb1EQ2qvGDFmIcKiZ4MH1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92563c60b66ab07fef3f05994c3e6e0ae627a89efbd16b00ec791fccc9f9ece4","last_reissued_at":"2026-07-05T10:15:04.236828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:04.236828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MasRouter: Learning to Route LLMs for Multi-Agent Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Boyang Liu, Dawei Cheng, Guancheng Wan, Guibin Zhang, Kun Wang, Yanwei Yue, Yiyan Qi","submitted_at":"2025-02-16T14:00:59Z","abstract_excerpt":"Multi-agent systems (MAS) powered by Large Language Models (LLMs) have been demonstrated to push the boundaries of LLM capabilities, yet they often incur significant costs and face challenges in dynamic LLM selection. Current LLM routing methods effectively reduce overhead in single-agent scenarios by customizing LLM selection for each query, but they overlook the critical decisions regarding collaboration modes and agent roles in MAS. In response to this challenge, we first introduce the problem of Multi-Agent System Routing (MASR), which integrates all components of MAS into a unified routin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11133","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/2502.11133/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":"2502.11133","created_at":"2026-07-05T10:15:04.236887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11133v1","created_at":"2026-07-05T10:15:04.236887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11133","created_at":"2026-07-05T10:15:04.236887+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJLDYYFWNKYH","created_at":"2026-07-05T10:15:04.236887+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJLDYYFWNKYH73Z7","created_at":"2026-07-05T10:15:04.236887+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJLDYYFW","created_at":"2026-07-05T10:15:04.236887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07989","citing_title":"Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2606.05704","citing_title":"Critic-Guided Heterogeneous Multi-Agent Reasoning for Reliable Mathematical Problem Solving","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.04695","citing_title":"TRINITY: An Evolved LLM Coordinator","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27771","citing_title":"Emergent Social Intelligence Risks in Generative Multi-Agent Systems","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13647","citing_title":"FlowCompile: An Optimizing Compiler for Structured LLM Workflows","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02863","citing_title":"EMS: Multi-Agent Voting via Efficient Majority-then-Stopping","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05657","citing_title":"Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07180","citing_title":"Learning Agent Routing From Early Experience","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJLDYYFWNKYH73Z7AWMUYPTOBL","json":"https://pith.science/pith/SJLDYYFWNKYH73Z7AWMUYPTOBL.json","graph_json":"https://pith.science/api/pith-number/SJLDYYFWNKYH73Z7AWMUYPTOBL/graph.json","events_json":"https://pith.science/api/pith-number/SJLDYYFWNKYH73Z7AWMUYPTOBL/events.json","paper":"https://pith.science/paper/SJLDYYFW"},"agent_actions":{"view_html":"https://pith.science/pith/SJLDYYFWNKYH73Z7AWMUYPTOBL","download_json":"https://pith.science/pith/SJLDYYFWNKYH73Z7AWMUYPTOBL.json","view_paper":"https://pith.science/paper/SJLDYYFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11133&json=true","fetch_graph":"https://pith.science/api/pith-number/SJLDYYFWNKYH73Z7AWMUYPTOBL/graph.json","fetch_events":"https://pith.science/api/pith-number/SJLDYYFWNKYH73Z7AWMUYPTOBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJLDYYFWNKYH73Z7AWMUYPTOBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJLDYYFWNKYH73Z7AWMUYPTOBL/action/storage_attestation","attest_author":"https://pith.science/pith/SJLDYYFWNKYH73Z7AWMUYPTOBL/action/author_attestation","sign_citation":"https://pith.science/pith/SJLDYYFWNKYH73Z7AWMUYPTOBL/action/citation_signature","submit_replication":"https://pith.science/pith/SJLDYYFWNKYH73Z7AWMUYPTOBL/action/replication_record"}},"created_at":"2026-07-05T10:15:04.236887+00:00","updated_at":"2026-07-05T10:15:04.236887+00:00"}