{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5DYB3MBWHZC27YBMPTN45QLADP","short_pith_number":"pith:5DYB3MBW","schema_version":"1.0","canonical_sha256":"e8f01db0363e45afe02c7cdbcec1601bebb089488c2eb370a7b430bcf1767317","source":{"kind":"arxiv","id":"2408.09955","version":3},"attestation_state":"computed","paper":{"title":"MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Bingsheng He, Jingsheng Liang, Nuo Chen, Qian Wang, Qinbin Li, Tianyu Wang, Zhenheng Tang","submitted_at":"2024-08-19T12:55:16Z","abstract_excerpt":"LLM-based multi-agent systems (MAS) have shown promise in tackling complex tasks. However, existing solutions often suffer from limited agent coordination and heavy reliance on predefined Standard Operating Procedures (SOPs), which demand extensive human input. To address these limitations, we propose MegaAgent, a large-scale autonomous LLM-based multi-agent system. MegaAgent generates agents based on task complexity and enables dynamic task decomposition, parallel execution, efficient communication, and comprehensive system monitoring of agents. In evaluations, MegaAgent demonstrates exceptio"},"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":"2408.09955","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2024-08-19T12:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"80007eb588be387ba544856dc938291cb4352b63513f546a920ec6317700502a","abstract_canon_sha256":"c544123b36420358929fdaeef0b605ceeffaf26e9ef9ee0426fdf11b06117934"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:34.110699Z","signature_b64":"3g51re6R+ZvSCBYI8st6i8spa/bFm0ClMEE1RpCu07SySN2tTGcnH29KiCSWZvatfL6BY37TFUD3KDHIz1b8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f01db0363e45afe02c7cdbcec1601bebb089488c2eb370a7b430bcf1767317","last_reissued_at":"2026-07-05T11:11:34.110163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:34.110163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Bingsheng He, Jingsheng Liang, Nuo Chen, Qian Wang, Qinbin Li, Tianyu Wang, Zhenheng Tang","submitted_at":"2024-08-19T12:55:16Z","abstract_excerpt":"LLM-based multi-agent systems (MAS) have shown promise in tackling complex tasks. However, existing solutions often suffer from limited agent coordination and heavy reliance on predefined Standard Operating Procedures (SOPs), which demand extensive human input. To address these limitations, we propose MegaAgent, a large-scale autonomous LLM-based multi-agent system. MegaAgent generates agents based on task complexity and enables dynamic task decomposition, parallel execution, efficient communication, and comprehensive system monitoring of agents. In evaluations, MegaAgent demonstrates exceptio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09955","kind":"arxiv","version":3},"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/2408.09955/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":"2408.09955","created_at":"2026-07-05T11:11:34.110232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.09955v3","created_at":"2026-07-05T11:11:34.110232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09955","created_at":"2026-07-05T11:11:34.110232+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DYB3MBWHZC2","created_at":"2026-07-05T11:11:34.110232+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DYB3MBWHZC27YBM","created_at":"2026-07-05T11:11:34.110232+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DYB3MBW","created_at":"2026-07-05T11:11:34.110232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30602","citing_title":"MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11336","citing_title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5DYB3MBWHZC27YBMPTN45QLADP","json":"https://pith.science/pith/5DYB3MBWHZC27YBMPTN45QLADP.json","graph_json":"https://pith.science/api/pith-number/5DYB3MBWHZC27YBMPTN45QLADP/graph.json","events_json":"https://pith.science/api/pith-number/5DYB3MBWHZC27YBMPTN45QLADP/events.json","paper":"https://pith.science/paper/5DYB3MBW"},"agent_actions":{"view_html":"https://pith.science/pith/5DYB3MBWHZC27YBMPTN45QLADP","download_json":"https://pith.science/pith/5DYB3MBWHZC27YBMPTN45QLADP.json","view_paper":"https://pith.science/paper/5DYB3MBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.09955&json=true","fetch_graph":"https://pith.science/api/pith-number/5DYB3MBWHZC27YBMPTN45QLADP/graph.json","fetch_events":"https://pith.science/api/pith-number/5DYB3MBWHZC27YBMPTN45QLADP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DYB3MBWHZC27YBMPTN45QLADP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DYB3MBWHZC27YBMPTN45QLADP/action/storage_attestation","attest_author":"https://pith.science/pith/5DYB3MBWHZC27YBMPTN45QLADP/action/author_attestation","sign_citation":"https://pith.science/pith/5DYB3MBWHZC27YBMPTN45QLADP/action/citation_signature","submit_replication":"https://pith.science/pith/5DYB3MBWHZC27YBMPTN45QLADP/action/replication_record"}},"created_at":"2026-07-05T11:11:34.110232+00:00","updated_at":"2026-07-05T11:11:34.110232+00:00"}