{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MBJWQ5CZWGLECBAPOJB7Z5HNM7","short_pith_number":"pith:MBJWQ5CZ","schema_version":"1.0","canonical_sha256":"6053687459b19641040f7243fcf4ed67eced8c45c5be4943a3591f82786d00ed","source":{"kind":"arxiv","id":"2502.00674","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chi Jin, Mengzhou Xia, Wenzhe Li, Yong Lin","submitted_at":"2025-02-02T05:23:29Z","abstract_excerpt":"Ensembling outputs from diverse sources is a straightforward yet effective approach to boost performance. Mixture-of-Agents (MoA) is one such popular ensemble method that aggregates outputs from multiple different Large Language Models (LLMs). This paper raises the question in the context of language models: is mixing different LLMs truly beneficial? We propose Self-MoA -- an ensemble method that aggregates outputs from only the single top-performing LLM. Our extensive experiments reveal that, surprisingly, Self-MoA outperforms standard MoA that mixes different LLMs in a large number of scenar"},"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":"2502.00674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T05:23:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be5567980b4ea5eeb31a3ca39c06aafbe071f5afb45ff95850831dd222071432","abstract_canon_sha256":"9bcf79ae48662db5d9f7b7e8b80881d91f1a9d8dd101987635676224b8a49e73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:36.976430Z","signature_b64":"+ibNXnAj/DQZprVfeMpcIN2HX6WegIAn39d+PvS3H2K/O7Z4Qt/hXyDn1C9PAyPPe/TbPP6bjja3o4gzmqS6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6053687459b19641040f7243fcf4ed67eced8c45c5be4943a3591f82786d00ed","last_reissued_at":"2026-07-05T10:08:36.975945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:36.975945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chi Jin, Mengzhou Xia, Wenzhe Li, Yong Lin","submitted_at":"2025-02-02T05:23:29Z","abstract_excerpt":"Ensembling outputs from diverse sources is a straightforward yet effective approach to boost performance. Mixture-of-Agents (MoA) is one such popular ensemble method that aggregates outputs from multiple different Large Language Models (LLMs). This paper raises the question in the context of language models: is mixing different LLMs truly beneficial? We propose Self-MoA -- an ensemble method that aggregates outputs from only the single top-performing LLM. Our extensive experiments reveal that, surprisingly, Self-MoA outperforms standard MoA that mixes different LLMs in a large number of scenar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00674","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/2502.00674/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":"2502.00674","created_at":"2026-07-05T10:08:36.976005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00674v1","created_at":"2026-07-05T10:08:36.976005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00674","created_at":"2026-07-05T10:08:36.976005+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBJWQ5CZWGLE","created_at":"2026-07-05T10:08:36.976005+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBJWQ5CZWGLECBAP","created_at":"2026-07-05T10:08:36.976005+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBJWQ5CZ","created_at":"2026-07-05T10:08:36.976005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07690","citing_title":"Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24437","citing_title":"ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27288","citing_title":"When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":142,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06941","citing_title":"Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03544","citing_title":"SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03014","citing_title":"MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency","ref_index":169,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02646","citing_title":"The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00405","citing_title":"From Talking Words to Sharing Thoughts: Scalable Multi-LLM Aggregation via Structured Message Passing","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14200","citing_title":"A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19418","citing_title":"Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21159","citing_title":"MAC: Masked Agent Collaboration Boosts Large Language Model Medical Decision-Making","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2512.22579","citing_title":"SANet: A Semantic-aware Agentic AI Networking Framework for Cross-layer Optimization in 6G","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2602.19509","citing_title":"Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09121","citing_title":"A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21950","citing_title":"Feedback Over Form: Why Execution Feedback Matters More Than Pipeline Topology in 1-3B Code Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19049","citing_title":"Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBJWQ5CZWGLECBAPOJB7Z5HNM7","json":"https://pith.science/pith/MBJWQ5CZWGLECBAPOJB7Z5HNM7.json","graph_json":"https://pith.science/api/pith-number/MBJWQ5CZWGLECBAPOJB7Z5HNM7/graph.json","events_json":"https://pith.science/api/pith-number/MBJWQ5CZWGLECBAPOJB7Z5HNM7/events.json","paper":"https://pith.science/paper/MBJWQ5CZ"},"agent_actions":{"view_html":"https://pith.science/pith/MBJWQ5CZWGLECBAPOJB7Z5HNM7","download_json":"https://pith.science/pith/MBJWQ5CZWGLECBAPOJB7Z5HNM7.json","view_paper":"https://pith.science/paper/MBJWQ5CZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00674&json=true","fetch_graph":"https://pith.science/api/pith-number/MBJWQ5CZWGLECBAPOJB7Z5HNM7/graph.json","fetch_events":"https://pith.science/api/pith-number/MBJWQ5CZWGLECBAPOJB7Z5HNM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBJWQ5CZWGLECBAPOJB7Z5HNM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBJWQ5CZWGLECBAPOJB7Z5HNM7/action/storage_attestation","attest_author":"https://pith.science/pith/MBJWQ5CZWGLECBAPOJB7Z5HNM7/action/author_attestation","sign_citation":"https://pith.science/pith/MBJWQ5CZWGLECBAPOJB7Z5HNM7/action/citation_signature","submit_replication":"https://pith.science/pith/MBJWQ5CZWGLECBAPOJB7Z5HNM7/action/replication_record"}},"created_at":"2026-07-05T10:08:36.976005+00:00","updated_at":"2026-07-05T10:08:36.976005+00:00"}