{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6FW55WTH7SY5ERVLUKMNIUZVPA","short_pith_number":"pith:6FW55WTH","schema_version":"1.0","canonical_sha256":"f16ddeda67fcb1d246aba298d45335783b4575a8583f23991ab0e9456254843a","source":{"kind":"arxiv","id":"2501.10053","version":3},"attestation_state":"computed","paper":{"title":"AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chuzhan Hao, Guochao Jiang, Hao Wang, Jingyi Song, Wenfeng Feng, Yuewei Zhang","submitted_at":"2025-01-17T09:16:13Z","abstract_excerpt":"Leveraging the autonomous decision-making capabilities of large language models (LLMs) has demonstrated superior performance in reasoning tasks. However, despite the success of iterative or agentic retrieval-augmented generation (RAG) techniques, these methods are often constrained to a single solution space when confronted with complex problems. In this paper, we propose a novel thinking pattern in RAG that integrates autonomous strategic planning with efficient reasoning actions, significantly activating intrinsic reasoning capabilities and expanding the solution space of specific tasks via "},"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":"2501.10053","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-01-17T09:16:13Z","cross_cats_sorted":[],"title_canon_sha256":"55380ed404db2b2471233ed4a71227b0d3a672c700b1ea0cb7cf0621dbfd5c22","abstract_canon_sha256":"a8334eb6d6eb917d0e7caacee3e3f5c77de7af1ee724033556b16dd8ba34f664"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:56.798550Z","signature_b64":"dz15GxN9stf7CB9tknJpSslNXNGLliD6UDiCii1kRs9DTAW50vu6UCFQU+l0nGz+NCqhdFdmgxPPQK9zR8ViBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f16ddeda67fcb1d246aba298d45335783b4575a8583f23991ab0e9456254843a","last_reissued_at":"2026-07-05T11:59:56.798087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:56.798087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chuzhan Hao, Guochao Jiang, Hao Wang, Jingyi Song, Wenfeng Feng, Yuewei Zhang","submitted_at":"2025-01-17T09:16:13Z","abstract_excerpt":"Leveraging the autonomous decision-making capabilities of large language models (LLMs) has demonstrated superior performance in reasoning tasks. However, despite the success of iterative or agentic retrieval-augmented generation (RAG) techniques, these methods are often constrained to a single solution space when confronted with complex problems. In this paper, we propose a novel thinking pattern in RAG that integrates autonomous strategic planning with efficient reasoning actions, significantly activating intrinsic reasoning capabilities and expanding the solution space of specific tasks via "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10053","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/2501.10053/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":"2501.10053","created_at":"2026-07-05T11:59:56.798146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10053v3","created_at":"2026-07-05T11:59:56.798146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10053","created_at":"2026-07-05T11:59:56.798146+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FW55WTH7SY5","created_at":"2026-07-05T11:59:56.798146+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FW55WTH7SY5ERVL","created_at":"2026-07-05T11:59:56.798146+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FW55WTH","created_at":"2026-07-05T11:59:56.798146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6FW55WTH7SY5ERVLUKMNIUZVPA","json":"https://pith.science/pith/6FW55WTH7SY5ERVLUKMNIUZVPA.json","graph_json":"https://pith.science/api/pith-number/6FW55WTH7SY5ERVLUKMNIUZVPA/graph.json","events_json":"https://pith.science/api/pith-number/6FW55WTH7SY5ERVLUKMNIUZVPA/events.json","paper":"https://pith.science/paper/6FW55WTH"},"agent_actions":{"view_html":"https://pith.science/pith/6FW55WTH7SY5ERVLUKMNIUZVPA","download_json":"https://pith.science/pith/6FW55WTH7SY5ERVLUKMNIUZVPA.json","view_paper":"https://pith.science/paper/6FW55WTH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10053&json=true","fetch_graph":"https://pith.science/api/pith-number/6FW55WTH7SY5ERVLUKMNIUZVPA/graph.json","fetch_events":"https://pith.science/api/pith-number/6FW55WTH7SY5ERVLUKMNIUZVPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FW55WTH7SY5ERVLUKMNIUZVPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FW55WTH7SY5ERVLUKMNIUZVPA/action/storage_attestation","attest_author":"https://pith.science/pith/6FW55WTH7SY5ERVLUKMNIUZVPA/action/author_attestation","sign_citation":"https://pith.science/pith/6FW55WTH7SY5ERVLUKMNIUZVPA/action/citation_signature","submit_replication":"https://pith.science/pith/6FW55WTH7SY5ERVLUKMNIUZVPA/action/replication_record"}},"created_at":"2026-07-05T11:59:56.798146+00:00","updated_at":"2026-07-05T11:59:56.798146+00:00"}