{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X6V4RZSOLCA52WFRZIGSYD7I5O","short_pith_number":"pith:X6V4RZSO","schema_version":"1.0","canonical_sha256":"bfabc8e64e5881dd58b1ca0d2c0fe8eba2c83e599f10a9bdddaf9ed3fc7d1352","source":{"kind":"arxiv","id":"2508.01005","version":1},"attestation_state":"computed","paper":{"title":"MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Erhan Zhang, Jiaxin Mao, Jizhou Huang, Lingyong Yan, Shuaiqiang Wang, Yiqun Chen","submitted_at":"2025-08-01T18:15:22Z","abstract_excerpt":"In question-answering (QA) systems, Retrieval-Augmented Generation (RAG) has become pivotal in enhancing response accuracy and reducing hallucination issues. The architecture of RAG systems varies significantly, encompassing single-round RAG, iterative RAG, and reasoning RAG, each tailored to address different types of queries. Due to the varying complexity of real-world queries, a fixed RAG pipeline often struggles to balance performance and cost efficiency across different queries. To address this challenge, we propose an adaptive RAG framework called MAO-ARAG, which leverages multi-agent or"},"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":"2508.01005","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T18:15:22Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e2febbac341b18c077618c5ed81eeb9f4e53ad92f76fe1fedf994c637c7e0a3c","abstract_canon_sha256":"812b2d9db02c46fc11b2df142ae8b10410c36ac81d7438ff1910ebae8021e022"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:31.627731Z","signature_b64":"KtdBcNfyhkO8PaB/doLlv9YxXp3vrJfkt9yoShQQyw6z8KUQbCnYrqheA9zf3unMubbvGdZZ1wr3rWvERnCyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfabc8e64e5881dd58b1ca0d2c0fe8eba2c83e599f10a9bdddaf9ed3fc7d1352","last_reissued_at":"2026-07-05T11:47:31.624990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:31.624990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAO-ARAG: Multi-Agent Orchestration for Adaptive Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Erhan Zhang, Jiaxin Mao, Jizhou Huang, Lingyong Yan, Shuaiqiang Wang, Yiqun Chen","submitted_at":"2025-08-01T18:15:22Z","abstract_excerpt":"In question-answering (QA) systems, Retrieval-Augmented Generation (RAG) has become pivotal in enhancing response accuracy and reducing hallucination issues. The architecture of RAG systems varies significantly, encompassing single-round RAG, iterative RAG, and reasoning RAG, each tailored to address different types of queries. Due to the varying complexity of real-world queries, a fixed RAG pipeline often struggles to balance performance and cost efficiency across different queries. To address this challenge, we propose an adaptive RAG framework called MAO-ARAG, which leverages multi-agent or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01005","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/2508.01005/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":"2508.01005","created_at":"2026-07-05T11:47:31.627159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01005v1","created_at":"2026-07-05T11:47:31.627159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01005","created_at":"2026-07-05T11:47:31.627159+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6V4RZSOLCA5","created_at":"2026-07-05T11:47:31.627159+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6V4RZSOLCA52WFR","created_at":"2026-07-05T11:47:31.627159+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6V4RZSO","created_at":"2026-07-05T11:47:31.627159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07548","citing_title":"Think Big, Search Small: Where Capacity Matters in Hierarchical Search Agents?","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03675","citing_title":"OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25676","citing_title":"CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6V4RZSOLCA52WFRZIGSYD7I5O","json":"https://pith.science/pith/X6V4RZSOLCA52WFRZIGSYD7I5O.json","graph_json":"https://pith.science/api/pith-number/X6V4RZSOLCA52WFRZIGSYD7I5O/graph.json","events_json":"https://pith.science/api/pith-number/X6V4RZSOLCA52WFRZIGSYD7I5O/events.json","paper":"https://pith.science/paper/X6V4RZSO"},"agent_actions":{"view_html":"https://pith.science/pith/X6V4RZSOLCA52WFRZIGSYD7I5O","download_json":"https://pith.science/pith/X6V4RZSOLCA52WFRZIGSYD7I5O.json","view_paper":"https://pith.science/paper/X6V4RZSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01005&json=true","fetch_graph":"https://pith.science/api/pith-number/X6V4RZSOLCA52WFRZIGSYD7I5O/graph.json","fetch_events":"https://pith.science/api/pith-number/X6V4RZSOLCA52WFRZIGSYD7I5O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6V4RZSOLCA52WFRZIGSYD7I5O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6V4RZSOLCA52WFRZIGSYD7I5O/action/storage_attestation","attest_author":"https://pith.science/pith/X6V4RZSOLCA52WFRZIGSYD7I5O/action/author_attestation","sign_citation":"https://pith.science/pith/X6V4RZSOLCA52WFRZIGSYD7I5O/action/citation_signature","submit_replication":"https://pith.science/pith/X6V4RZSOLCA52WFRZIGSYD7I5O/action/replication_record"}},"created_at":"2026-07-05T11:47:31.627159+00:00","updated_at":"2026-07-05T11:47:31.627159+00:00"}