{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ODIPMCC46MLGH3BLAI2F7IRCC4","short_pith_number":"pith:ODIPMCC4","schema_version":"1.0","canonical_sha256":"70d0f6085cf31663ec2b02345fa222171b6b616cc905456fc451a7e01baaceaf","source":{"kind":"arxiv","id":"2505.24442","version":1},"attestation_state":"computed","paper":{"title":"RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengcheng Han, Jiabao Zhao, Jinxin Shi, Wenjun Cui, Xingjiao Wu, Xin Zhao, Zhentao Xie","submitted_at":"2025-05-30T10:23:11Z","abstract_excerpt":"Although multi-agent systems based on large language models show strong capabilities on multiple tasks, they are still limited by high computational overhead, information loss, and robustness. Inspired by ResNet's residual learning, we propose Residual Mixture-of-Agents (RMoA), integrating residual connections to optimize efficiency and reliability. To maximize information utilization from model responses while minimizing computational costs, we innovatively design an embedding-based diversity selection mechanism that greedily selects responses via vector similarity. Furthermore, to mitigate i"},"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":"2505.24442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T10:23:11Z","cross_cats_sorted":[],"title_canon_sha256":"4f9be437bf61c8c6f5b2ee27ef31eb904e5d98bc7f676634e9fe4bcdeee2fd0f","abstract_canon_sha256":"48adda8cb4696d677b4efbcb560d04033c3dee6548c73c51a02e07a42dfb2d9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:49.858883Z","signature_b64":"p8QsYViWzxs0uj2N/QXqngtTLD35Zjbq5uRosb7ekFCvL3aDk0bmS1xsTehsvVHzF6Z+jNkFveb57NGL7Ok1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70d0f6085cf31663ec2b02345fa222171b6b616cc905456fc451a7e01baaceaf","last_reissued_at":"2026-07-05T11:12:49.858345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:49.858345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengcheng Han, Jiabao Zhao, Jinxin Shi, Wenjun Cui, Xingjiao Wu, Xin Zhao, Zhentao Xie","submitted_at":"2025-05-30T10:23:11Z","abstract_excerpt":"Although multi-agent systems based on large language models show strong capabilities on multiple tasks, they are still limited by high computational overhead, information loss, and robustness. Inspired by ResNet's residual learning, we propose Residual Mixture-of-Agents (RMoA), integrating residual connections to optimize efficiency and reliability. To maximize information utilization from model responses while minimizing computational costs, we innovatively design an embedding-based diversity selection mechanism that greedily selects responses via vector similarity. Furthermore, to mitigate i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24442","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/2505.24442/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":"2505.24442","created_at":"2026-07-05T11:12:49.858408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24442v1","created_at":"2026-07-05T11:12:49.858408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24442","created_at":"2026-07-05T11:12:49.858408+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODIPMCC46MLG","created_at":"2026-07-05T11:12:49.858408+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODIPMCC46MLGH3BL","created_at":"2026-07-05T11:12:49.858408+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODIPMCC4","created_at":"2026-07-05T11:12:49.858408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.02209","citing_title":"Balancing Information Accuracy and Response Timeliness in Networked LLMs","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODIPMCC46MLGH3BLAI2F7IRCC4","json":"https://pith.science/pith/ODIPMCC46MLGH3BLAI2F7IRCC4.json","graph_json":"https://pith.science/api/pith-number/ODIPMCC46MLGH3BLAI2F7IRCC4/graph.json","events_json":"https://pith.science/api/pith-number/ODIPMCC46MLGH3BLAI2F7IRCC4/events.json","paper":"https://pith.science/paper/ODIPMCC4"},"agent_actions":{"view_html":"https://pith.science/pith/ODIPMCC46MLGH3BLAI2F7IRCC4","download_json":"https://pith.science/pith/ODIPMCC46MLGH3BLAI2F7IRCC4.json","view_paper":"https://pith.science/paper/ODIPMCC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24442&json=true","fetch_graph":"https://pith.science/api/pith-number/ODIPMCC46MLGH3BLAI2F7IRCC4/graph.json","fetch_events":"https://pith.science/api/pith-number/ODIPMCC46MLGH3BLAI2F7IRCC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODIPMCC46MLGH3BLAI2F7IRCC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODIPMCC46MLGH3BLAI2F7IRCC4/action/storage_attestation","attest_author":"https://pith.science/pith/ODIPMCC46MLGH3BLAI2F7IRCC4/action/author_attestation","sign_citation":"https://pith.science/pith/ODIPMCC46MLGH3BLAI2F7IRCC4/action/citation_signature","submit_replication":"https://pith.science/pith/ODIPMCC46MLGH3BLAI2F7IRCC4/action/replication_record"}},"created_at":"2026-07-05T11:12:49.858408+00:00","updated_at":"2026-07-05T11:12:49.858408+00:00"}