{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/r1-searcher-incentivizing-the-dynamic","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning","arxiv_id":"2505.17005","date":"2025-05-22","proceeding":null,"authors":["Huatong Song","Jinhao Jiang","Wenqing Tian","Zhipeng Chen","YuHuan Wu","Jiahao Zhao","Yingqian Min","Wayne Xin Zhao","Lei Fang","Ji-Rong Wen"],"abstract":"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. The RL stage uses outcome-supervision to encourage exploration, incorporates a reward mechanism for internal knowledge utilization, and integrates a memorization mechanism to continuously assimilate retrieved information, thereby enriching the model's internal knowledge. By leveraging internal knowledge and external search engine, the model continuously improves its capabilities, enabling efficient retrieval-augmented reasoning. Our experiments demonstrate that R1-Searcher++ outperforms previous RAG and reasoning methods and achieves efficient retrieval. The code is available at https://github.com/RUCAIBox/R1-Searcher-plus.","url_abs":"https://arxiv.org/abs/2505.17005v1","url_pdf":"https://arxiv.org/pdf/2505.17005v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"r1-searcher-incentivizing-the-dynamic","repo_url":"https://github.com/rucaibox/r1-searcher-plus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"r1-searcher-incentivizing-the-dynamic","repo_url":"https://github.com/RUCAIBox/R1-Searcher","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"r1-searcher-incentivizing-the-dynamic","repo_url":"https://github.com/rucaibox/simpledeepsearcher","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"rag","task_name":"RAG"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"rag","method_name":"RAG"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sft","method_name":"SFT"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.17005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17005"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/RUCAIBox/R1-Searcher","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rucaibox/simpledeepsearcher","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rucaibox/r1-searcher-plus","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"listed":{"samples":10,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"d22718d531542ab7","entry":"normalize_answer","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"evaluation/metric_calc_rule.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/evaluation/metric_calc_rule.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d22718d531542ab7"}},{"code_sha256_prefix":"bd03a63e354ac8d3","entry":"bing_web_search","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"evaluation/eval_search_online.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/evaluation/eval_search_online.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd03a63e354ac8d3"}},{"code_sha256_prefix":"60508530d397bd36","entry":"bool_mapping","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"evaluation/metric_calc_rule.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/evaluation/metric_calc_rule.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60508530d397bd36"}},{"code_sha256_prefix":"c2d09307ece3ffdf","entry":"cover_exact_match_score_1","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"train/reward_server_llama_stage1.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/train/reward_server_llama_stage1.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2d09307ece3ffdf"}},{"code_sha256_prefix":"1332ed2c182add91","entry":"exact_match_score","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"train/reward_server_qwen_zero.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/train/reward_server_qwen_zero.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1332ed2c182add91"}},{"code_sha256_prefix":"6793613f488defee","entry":"extract_relevant_info","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"evaluation/eval_search_online.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/evaluation/eval_search_online.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6793613f488defee"}},{"code_sha256_prefix":"53d9c134452ad7d1","entry":"f1_score","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"evaluation/metric_calc_rule.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/evaluation/metric_calc_rule.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"53d9c134452ad7d1"}},{"code_sha256_prefix":"323c01eff1603dc2","entry":"load_corpus","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"train/wiki_corpus_load.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/train/wiki_corpus_load.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"323c01eff1603dc2"}},{"code_sha256_prefix":"64ee1085455df662","entry":"load_corpus","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"wiki_corpus_index_bulid/build_corpus_embedding.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/wiki_corpus_index_bulid/build_corpus_embedding.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64ee1085455df662"}},{"code_sha256_prefix":"beb27b94356d1280","entry":"process_text","repo":"RUCAIBox/R1-Searcher","repo_kind":"listed","path":"evaluation/eval_search_loacl.py","file_url":"https://github.com/RUCAIBox/R1-Searcher/blob/HEAD/evaluation/eval_search_loacl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"beb27b94356d1280"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}