{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QNX7NSXEBQV4YV6UJFXQSDOND5","short_pith_number":"pith:QNX7NSXE","schema_version":"1.0","canonical_sha256":"836ff6cae40c2bcc57d4496f090dcd1f4ab9bfda677841b61aae0a3a41e50baf","source":{"kind":"arxiv","id":"2601.23219","version":2},"attestation_state":"computed","paper":{"title":"MonoScale: Scaling Multi-Agent System with Monotonic Improvement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Bingwei Lu, Shuai Shao, Weinan Zhang, Yixiang Liu","submitted_at":"2026-01-30T17:44:49Z","abstract_excerpt":"In recent years, LLM-based multi-agent systems (MAS) have advanced rapidly, using a router to decompose tasks and delegate subtasks to specialized agents. A natural way to expand capability is to scale up the agent pool by continually integrating new functional agents or tool interfaces, but naive expansion can trigger performance collapse when the router cold-starts on newly added, heterogeneous, and unreliable agents. We propose MonoScale, an expansion-aware update framework that proactively generates a small set of agent-conditioned familiarization tasks, harvests evidence from both success"},"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":"2601.23219","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-01-30T17:44:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c02eb6dee2f49ac9ba216edd77aa0bfa9a55b76ec324c1ab2d88cc73539067d2","abstract_canon_sha256":"574455052353d51f3130a74cb755c7306e0dc97866243c6001e3baf7aece1791"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:17.469522Z","signature_b64":"tIOD8wEaXyU7u12tOVGguaZrCcxd6ZDnW5tH5VInd+U6hRvT4sn50h8N1bjqrOs8DEPfPnbou9SXvdxPZLkxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"836ff6cae40c2bcc57d4496f090dcd1f4ab9bfda677841b61aae0a3a41e50baf","last_reissued_at":"2026-05-22T01:03:17.468440Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:17.468440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MonoScale: Scaling Multi-Agent System with Monotonic Improvement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Bingwei Lu, Shuai Shao, Weinan Zhang, Yixiang Liu","submitted_at":"2026-01-30T17:44:49Z","abstract_excerpt":"In recent years, LLM-based multi-agent systems (MAS) have advanced rapidly, using a router to decompose tasks and delegate subtasks to specialized agents. A natural way to expand capability is to scale up the agent pool by continually integrating new functional agents or tool interfaces, but naive expansion can trigger performance collapse when the router cold-starts on newly added, heterogeneous, and unreliable agents. We propose MonoScale, an expansion-aware update framework that proactively generates a small set of agent-conditioned familiarization tasks, harvests evidence from both success"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.23219","kind":"arxiv","version":2},"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/2601.23219/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":"2601.23219","created_at":"2026-05-22T01:03:17.468612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.23219v2","created_at":"2026-05-22T01:03:17.468612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.23219","created_at":"2026-05-22T01:03:17.468612+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNX7NSXEBQV4","created_at":"2026-05-22T01:03:17.468612+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNX7NSXEBQV4YV6U","created_at":"2026-05-22T01:03:17.468612+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNX7NSXE","created_at":"2026-05-22T01:03:17.468612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.05657","citing_title":"Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation","ref_index":87,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNX7NSXEBQV4YV6UJFXQSDOND5","json":"https://pith.science/pith/QNX7NSXEBQV4YV6UJFXQSDOND5.json","graph_json":"https://pith.science/api/pith-number/QNX7NSXEBQV4YV6UJFXQSDOND5/graph.json","events_json":"https://pith.science/api/pith-number/QNX7NSXEBQV4YV6UJFXQSDOND5/events.json","paper":"https://pith.science/paper/QNX7NSXE"},"agent_actions":{"view_html":"https://pith.science/pith/QNX7NSXEBQV4YV6UJFXQSDOND5","download_json":"https://pith.science/pith/QNX7NSXEBQV4YV6UJFXQSDOND5.json","view_paper":"https://pith.science/paper/QNX7NSXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.23219&json=true","fetch_graph":"https://pith.science/api/pith-number/QNX7NSXEBQV4YV6UJFXQSDOND5/graph.json","fetch_events":"https://pith.science/api/pith-number/QNX7NSXEBQV4YV6UJFXQSDOND5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNX7NSXEBQV4YV6UJFXQSDOND5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNX7NSXEBQV4YV6UJFXQSDOND5/action/storage_attestation","attest_author":"https://pith.science/pith/QNX7NSXEBQV4YV6UJFXQSDOND5/action/author_attestation","sign_citation":"https://pith.science/pith/QNX7NSXEBQV4YV6UJFXQSDOND5/action/citation_signature","submit_replication":"https://pith.science/pith/QNX7NSXEBQV4YV6UJFXQSDOND5/action/replication_record"}},"created_at":"2026-05-22T01:03:17.468612+00:00","updated_at":"2026-05-22T01:03:17.468612+00:00"}