{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5GXVIBU26VQ77H3ID7SKLBW7KF","short_pith_number":"pith:5GXVIBU2","schema_version":"1.0","canonical_sha256":"e9af54069af561ff9f681fe4a586df5176f0b5697a5cb1c22974bba3f492273b","source":{"kind":"arxiv","id":"2505.22571","version":3},"attestation_state":"computed","paper":{"title":"Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Hoang Pham, Khac-Hoai Nam Bui, Thuy-Duong Nguyen","submitted_at":"2025-05-28T16:46:31Z","abstract_excerpt":"This paper presents a novel approach for unified retrieval-augmented generation (RAG) systems using the recent emerging large language model (LLM) agent concept. Specifically, Agent LLM, which utilizes LLM as fundamental controllers, has become a promising approach to enable the interpretability of RAG tasks, especially for complex reasoning question-answering systems (e.g., multi-hop queries). Nonetheless, previous works mainly focus on solving RAG systems with either single-hop or multi-hop approaches separately, which limits the application of those approaches to real-world applications. In"},"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":"2505.22571","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T16:46:31Z","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"title_canon_sha256":"a5a8641b427daf9422c5bc410f6078601d9619053fd7df1ca2be25297fa02d2b","abstract_canon_sha256":"14340691118c4340d96f0f3bdb425e5efe99fb6ecd7e0c28d2756946cab1c253"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:34.295271Z","signature_b64":"sA/IBKIDKYWr/LqZIT3DbpPrWRAbOJORthwDv5FfBKku506YREuNkSN5frFLjHGsGyHhv6x35XRili3m8PlFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9af54069af561ff9f681fe4a586df5176f0b5697a5cb1c22974bba3f492273b","last_reissued_at":"2026-07-05T11:12:34.294702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:34.294702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Hoang Pham, Khac-Hoai Nam Bui, Thuy-Duong Nguyen","submitted_at":"2025-05-28T16:46:31Z","abstract_excerpt":"This paper presents a novel approach for unified retrieval-augmented generation (RAG) systems using the recent emerging large language model (LLM) agent concept. Specifically, Agent LLM, which utilizes LLM as fundamental controllers, has become a promising approach to enable the interpretability of RAG tasks, especially for complex reasoning question-answering systems (e.g., multi-hop queries). Nonetheless, previous works mainly focus on solving RAG systems with either single-hop or multi-hop approaches separately, which limits the application of those approaches to real-world applications. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22571","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/2505.22571/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":"2505.22571","created_at":"2026-07-05T11:12:34.294764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22571v3","created_at":"2026-07-05T11:12:34.294764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22571","created_at":"2026-07-05T11:12:34.294764+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GXVIBU26VQ7","created_at":"2026-07-05T11:12:34.294764+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GXVIBU26VQ77H3I","created_at":"2026-07-05T11:12:34.294764+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GXVIBU2","created_at":"2026-07-05T11:12:34.294764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GXVIBU26VQ77H3ID7SKLBW7KF","json":"https://pith.science/pith/5GXVIBU26VQ77H3ID7SKLBW7KF.json","graph_json":"https://pith.science/api/pith-number/5GXVIBU26VQ77H3ID7SKLBW7KF/graph.json","events_json":"https://pith.science/api/pith-number/5GXVIBU26VQ77H3ID7SKLBW7KF/events.json","paper":"https://pith.science/paper/5GXVIBU2"},"agent_actions":{"view_html":"https://pith.science/pith/5GXVIBU26VQ77H3ID7SKLBW7KF","download_json":"https://pith.science/pith/5GXVIBU26VQ77H3ID7SKLBW7KF.json","view_paper":"https://pith.science/paper/5GXVIBU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22571&json=true","fetch_graph":"https://pith.science/api/pith-number/5GXVIBU26VQ77H3ID7SKLBW7KF/graph.json","fetch_events":"https://pith.science/api/pith-number/5GXVIBU26VQ77H3ID7SKLBW7KF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GXVIBU26VQ77H3ID7SKLBW7KF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GXVIBU26VQ77H3ID7SKLBW7KF/action/storage_attestation","attest_author":"https://pith.science/pith/5GXVIBU26VQ77H3ID7SKLBW7KF/action/author_attestation","sign_citation":"https://pith.science/pith/5GXVIBU26VQ77H3ID7SKLBW7KF/action/citation_signature","submit_replication":"https://pith.science/pith/5GXVIBU26VQ77H3ID7SKLBW7KF/action/replication_record"}},"created_at":"2026-07-05T11:12:34.294764+00:00","updated_at":"2026-07-05T11:12:34.294764+00:00"}