Librarian Bot. I found the following papers similar to this paper.

\n

The following papers were recommended by the Semantic Scholar API

\n

\n
• Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs (2025)
\n
• Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent (2025)
\n
• SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis (2025)
\n
• Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging (2025)
\n
• LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025)
\n
• Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty (2025)
\n
• ZeroSearch: Incentivize the Search Capability of LLMs without Searching (2025)
\n

\n

Please give a thumbs up to this comment if you found it helpful!

\n

If you want recommendations for any Paper on Hugging Face checkout this Space

\n

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2025-05-29T01:40:11.063Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":264}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7287148833274841},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2505.17005","authors":[{"_id":"683469f0df7cbb5c08a0498a","name":"Huatong Song","hidden":false},{"_id":"683469f0df7cbb5c08a0498b","name":"Jinhao Jiang","hidden":false},{"_id":"683469f0df7cbb5c08a0498c","name":"Wenqing Tian","hidden":false},{"_id":"683469f0df7cbb5c08a0498d","name":"Zhipeng Chen","hidden":false},{"_id":"683469f0df7cbb5c08a0498e","name":"Yuhuan Wu","hidden":false},{"_id":"683469f0df7cbb5c08a0498f","name":"Jiahao Zhao","hidden":false},{"_id":"683469f0df7cbb5c08a04990","user":{"_id":"6703ac76ea890f0ca5b225eb","avatarUrl":"/avatars/5f56c49a1940143d47dd484782a4abbf.svg","isPro":false,"fullname":"Yingqian Min","user":"EliverQ","type":"user"},"name":"Yingqian Min","status":"claimed_verified","statusLastChangedAt":"2025-05-28T09:00:55.996Z","hidden":false},{"_id":"683469f0df7cbb5c08a04991","name":"Wayne Xin Zhao","hidden":false},{"_id":"683469f0df7cbb5c08a04992","name":"Lei Fang","hidden":false},{"_id":"683469f0df7cbb5c08a04993","name":"Ji-Rong Wen","hidden":false}],"publishedAt":"2025-05-22T17:58:26.000Z","submittedOnDailyAt":"2025-05-28T06:24:31.531Z","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs\n via Reinforcement Learning","submittedOnDailyBy":{"_id":"6703ac76ea890f0ca5b225eb","avatarUrl":"/avatars/5f56c49a1940143d47dd484782a4abbf.svg","isPro":false,"fullname":"Yingqian Min","user":"EliverQ","type":"user"},"summary":"Large Language Models (LLMs) are powerful but prone to hallucinations due to\nstatic knowledge. Retrieval-Augmented Generation (RAG) helps by injecting\nexternal information, but current methods often are costly, generalize poorly,\nor ignore the internal knowledge of the model. In this paper, we introduce\nR1-Searcher++, a novel framework designed to train LLMs to adaptively leverage\nboth internal and external knowledge sources. R1-Searcher++ employs a two-stage\ntraining strategy: an initial SFT Cold-start phase for preliminary format\nlearning, followed by RL for Dynamic Knowledge Acquisition. The RL stage uses\noutcome-supervision to encourage exploration, incorporates a reward mechanism\nfor internal knowledge utilization, and integrates a memorization mechanism to\ncontinuously assimilate retrieved information, thereby enriching the model's\ninternal knowledge. By leveraging internal knowledge and external search\nengine, the model continuously improves its capabilities, enabling efficient\nretrieval-augmented reasoning. Our experiments demonstrate that R1-Searcher++\noutperforms previous RAG and reasoning methods and achieves efficient\nretrieval. The code is available at\nhttps://github.com/RUCAIBox/R1-Searcher-plus.","upvotes":5,"discussionId":"683469f1df7cbb5c08a049b2","ai_summary":"R1-Searcher++, a novel framework, enhances LLMs by adaptively integrating internal and external knowledge through two-stage training, improving retrieval-augmented reasoning efficiency and performance.","ai_keywords":["Large Language Models (LLMs)","hallucinations","Retrieval-Augmented Generation (RAG)","R1-Searcher++","SFT Cold-start","Reinforcement Learning (RL)","outcome-supervision","reward mechanism","memorization mechanism","retrieval-augmented reasoning"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6703ac76ea890f0ca5b225eb","avatarUrl":"/avatars/5f56c49a1940143d47dd484782a4abbf.svg","isPro":false,"fullname":"Yingqian Min","user":"EliverQ","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"648eb1eb59c4e5c87dc116e0","avatarUrl":"/avatars/c636cea39c2c0937f01398c94ead5dad.svg","isPro":false,"fullname":"fdsqefsgergd","user":"T-representer","type":"user"},{"_id":"651c80a26ba9ab9b9582c273","avatarUrl":"/avatars/e963452eafd21f517d800f2e58e0f918.svg","isPro":false,"fullname":"siyeng feng","user":"siyengfeng","type":"user"},{"_id":"64d4615cf8082bf19b916492","avatarUrl":"/avatars/8e1b59565ec5e4b31090cf1b911781b9.svg","isPro":false,"fullname":"wongyukim","user":"wongyukim","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">