{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CUIB37BZZUFFFOKRO5OJ776QT5","short_pith_number":"pith:CUIB37BZ","schema_version":"1.0","canonical_sha256":"15101dfc39cd0a52b951775c9fffd09f65bd74025ea3342a9a4da4dbb1e9deb9","source":{"kind":"arxiv","id":"2507.09477","version":2},"attestation_state":"computed","paper":{"title":"Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunkit Chan, Dongyuan Li, Hai-Tao Zheng, Henry Peng Zou, Junyu Luo, Ming Zhang, Philip S. Yu, Renhe Jiang, Wei-Chieh Huang, Weizhi Zhang, Xiao Luo, Yangning Li, Yangqiu Song, Yankai Chen, Yaozu Wu, Yinghui Li, Yuanchen Bei, Yusheng Zhao, Yuyao Yang, Zhongfen Deng","submitted_at":"2025-07-13T03:29:41Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts. This survey synthesizes both strands under a unified reasoning-retrieval perspective. We first map how advanced reasoning optimizes each stage of RAG (Reasoning-Enhanced RAG). Then, we show how retrieved knowledge of different type supply missing premises and expand context for complex inference (RAG-Enhanced Reasoning). F"},"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":"2507.09477","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-13T03:29:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0f9ca8aba6bae90e3c11d72011d83aa9a92bacee09d1bda097f169754967e3fe","abstract_canon_sha256":"0496892708554a2020dddff48e1396c1210b33aa6350b202d61a0d49f4d007d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:09.278558Z","signature_b64":"2mQB4EhIR0o5yVkp7imDtipFzwuGd4IxZaFYX38ANBB9jS3FeUx1pJ48cnOxy1LuLuf7kb9zD3EevMk2OMF3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15101dfc39cd0a52b951775c9fffd09f65bd74025ea3342a9a4da4dbb1e9deb9","last_reissued_at":"2026-07-05T11:38:09.278022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:09.278022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunkit Chan, Dongyuan Li, Hai-Tao Zheng, Henry Peng Zou, Junyu Luo, Ming Zhang, Philip S. Yu, Renhe Jiang, Wei-Chieh Huang, Weizhi Zhang, Xiao Luo, Yangning Li, Yangqiu Song, Yankai Chen, Yaozu Wu, Yinghui Li, Yuanchen Bei, Yusheng Zhao, Yuyao Yang, Zhongfen Deng","submitted_at":"2025-07-13T03:29:41Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches often hallucinate or mis-ground facts. This survey synthesizes both strands under a unified reasoning-retrieval perspective. We first map how advanced reasoning optimizes each stage of RAG (Reasoning-Enhanced RAG). Then, we show how retrieved knowledge of different type supply missing premises and expand context for complex inference (RAG-Enhanced Reasoning). F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09477","kind":"arxiv","version":2},"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/2507.09477/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":"2507.09477","created_at":"2026-07-05T11:38:09.278081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09477v2","created_at":"2026-07-05T11:38:09.278081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09477","created_at":"2026-07-05T11:38:09.278081+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUIB37BZZUFF","created_at":"2026-07-05T11:38:09.278081+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUIB37BZZUFFFOKR","created_at":"2026-07-05T11:38:09.278081+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUIB37BZ","created_at":"2026-07-05T11:38:09.278081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27330","citing_title":"Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18203","citing_title":"RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27123","citing_title":"Rethinking Agentic RAG: Toward LLM-Driven Logical Retrieval Beyond Embeddings","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07843","citing_title":"RACT: Retrieval Augmented Column-Table Learning and Prediction for Multi-Table Schema Matching","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15170","citing_title":"Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13734","citing_title":"KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12285","citing_title":"GAM: Hierarchical Graph-based Agentic Memory for LLM Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14896","citing_title":"Toward Agentic RAG for Ukrainian","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CUIB37BZZUFFFOKRO5OJ776QT5","json":"https://pith.science/pith/CUIB37BZZUFFFOKRO5OJ776QT5.json","graph_json":"https://pith.science/api/pith-number/CUIB37BZZUFFFOKRO5OJ776QT5/graph.json","events_json":"https://pith.science/api/pith-number/CUIB37BZZUFFFOKRO5OJ776QT5/events.json","paper":"https://pith.science/paper/CUIB37BZ"},"agent_actions":{"view_html":"https://pith.science/pith/CUIB37BZZUFFFOKRO5OJ776QT5","download_json":"https://pith.science/pith/CUIB37BZZUFFFOKRO5OJ776QT5.json","view_paper":"https://pith.science/paper/CUIB37BZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09477&json=true","fetch_graph":"https://pith.science/api/pith-number/CUIB37BZZUFFFOKRO5OJ776QT5/graph.json","fetch_events":"https://pith.science/api/pith-number/CUIB37BZZUFFFOKRO5OJ776QT5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUIB37BZZUFFFOKRO5OJ776QT5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUIB37BZZUFFFOKRO5OJ776QT5/action/storage_attestation","attest_author":"https://pith.science/pith/CUIB37BZZUFFFOKRO5OJ776QT5/action/author_attestation","sign_citation":"https://pith.science/pith/CUIB37BZZUFFFOKRO5OJ776QT5/action/citation_signature","submit_replication":"https://pith.science/pith/CUIB37BZZUFFFOKRO5OJ776QT5/action/replication_record"}},"created_at":"2026-07-05T11:38:09.278081+00:00","updated_at":"2026-07-05T11:38:09.278081+00:00"}