{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KBGI2EQLAMIW7NKFALRFG7RLKI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"36386db39b7ceecc8d2e093de54b7dd501c306e41a7735f7010002b33dd16db6","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T17:58:26Z","title_canon_sha256":"4c42d957265fcbf0c67a4d5ce543545bc81c5039cc4195359338f77b38fec956"},"schema_version":"1.0","source":{"id":"2505.17005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17005","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17005v1","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17005","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"pith_short_12","alias_value":"KBGI2EQLAMIW","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"pith_short_16","alias_value":"KBGI2EQLAMIW7NKF","created_at":"2026-07-05T11:07:44Z"},{"alias_kind":"pith_short_8","alias_value":"KBGI2EQL","created_at":"2026-07-05T11:07:44Z"}],"graph_snapshots":[{"event_id":"sha256:594a43b3f7c9f08d6737bc967a2fadbdd52aa508597e2a05cd860ac78654025f","target":"graph","created_at":"2026-07-05T11:07:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.17005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are powerful but prone to hallucinations due to static knowledge. Retrieval-Augmented Generation (RAG) helps by injecting external information, but current methods often are costly, generalize poorly, or ignore the internal knowledge of the model. In this paper, we introduce R1-Searcher++, a novel framework designed to train LLMs to adaptively leverage both internal and external knowledge sources. R1-Searcher++ employs a two-stage training strategy: an initial SFT Cold-start phase for preliminary format learning, followed by RL for Dynamic Knowledge Acquisition. Th","authors_text":"Huatong Song, Jiahao Zhao, Jinhao Jiang, Ji-Rong Wen, Lei Fang, Wayne Xin Zhao, Wenqing Tian, Yingqian Min, Yuhuan Wu, Zhipeng Chen","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T17:58:26Z","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17005","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4c5d6545199b5f26e205405c7b0aa49943522600379d0ff7f1e4eaa7d32aff00","target":"record","created_at":"2026-07-05T11:07:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"36386db39b7ceecc8d2e093de54b7dd501c306e41a7735f7010002b33dd16db6","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T17:58:26Z","title_canon_sha256":"4c42d957265fcbf0c67a4d5ce543545bc81c5039cc4195359338f77b38fec956"},"schema_version":"1.0","source":{"id":"2505.17005","kind":"arxiv","version":1}},"canonical_sha256":"504c8d120b03116fb54502e2537e2b522c0e6dfb26f52d05c9cd6c21619f9e79","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"504c8d120b03116fb54502e2537e2b522c0e6dfb26f52d05c9cd6c21619f9e79","first_computed_at":"2026-07-05T11:07:44.428147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:44.428147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l1LWlC3Ph3NItk4vB8NVXs8bKxccnHvQhQktIk9zK57bxkdowDfrIp6frkCeti+iU9DqX6plyejzTDhDgt4MAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:44.428669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c5d6545199b5f26e205405c7b0aa49943522600379d0ff7f1e4eaa7d32aff00","sha256:594a43b3f7c9f08d6737bc967a2fadbdd52aa508597e2a05cd860ac78654025f"],"state_sha256":"c88e85ca6cda74374bb7c9553f6a15f78742fe1cac7500a3671c4fcd0bd3ce45"}