\n","updatedAt":"2025-03-26T02:26:07.106Z","author":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","fullname":"AK","name":"akhaliq","type":"user","isPro":false,"isHf":true,"isHfAdmin":false,"isMod":false,"followerCount":9175,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.3521834909915924},"editors":["akhaliq"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg"],"reactions":[],"isReport":false}},{"id":"67e4ab41765e3105ef07ee49","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":317,"isUserFollowing":false},"createdAt":"2025-03-27T01:34:57.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://huggingface.co/papers/2503.05592) (2025)\n* [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://huggingface.co/papers/2503.09516) (2025)\n* [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://huggingface.co/papers/2503.06749) (2025)\n* [Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering](https://huggingface.co/papers/2503.11197) (2025)\n* [Learning from Failures in Multi-Attempt Reinforcement Learning](https://huggingface.co/papers/2503.04808) (2025)\n* [RAG-Gym: Optimizing Reasoning and Search Agents with Process Supervision](https://huggingface.co/papers/2502.13957) (2025)\n* [Reinforcement Learning is all You Need](https://huggingface.co/papers/2503.09512) (2025)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

\n

The following papers were recommended by the Semantic Scholar API

\n

\n
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning (2025)
\n
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning (2025)
\n
• Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models (2025)
\n
• Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering (2025)
\n
• Learning from Failures in Multi-Attempt Reinforcement Learning (2025)
\n
• RAG-Gym: Optimizing Reasoning and Search Agents with Process Supervision (2025)
\n
• Reinforcement Learning is all You Need (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":"2025-03-27T01:34:57.565Z","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":317,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7530558109283447},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}},{"id":"67ea84fcabe646bb590232cd","author":{"_id":"6440b7c47bc3fbde138a1409","avatarUrl":"/avatars/d43ef8457f732c5e1753f96056b8ea8b.svg","fullname":"zhang","name":"Nurburgring","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":38,"isUserFollowing":false},"createdAt":"2025-03-31T12:05:16.000Z","type":"comment","data":{"edited":true,"hidden":true,"hiddenBy":"","hiddenReason":"Off-Topic","latest":{"raw":"This comment has been hidden","html":"This comment has been hidden","updatedAt":"2025-03-31T12:05:59.159Z","author":{"_id":"6440b7c47bc3fbde138a1409","avatarUrl":"/avatars/d43ef8457f732c5e1753f96056b8ea8b.svg","fullname":"zhang","name":"Nurburgring","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":38,"isUserFollowing":false}},"numEdits":0,"editors":[],"editorAvatarUrls":[],"reactions":[]}}],"primaryEmailConfirmed":false,"paper":{"id":"2503.19470","authors":[{"_id":"67e365b0dcfc2aeae1bf3da2","user":{"_id":"66254042ea4f4ed066a77a1e","avatarUrl":"/avatars/c749b77417431bb364f6fa2189eabaa2.svg","isPro":false,"fullname":"Mingyang Chen","user":"anselcmy","type":"user"},"name":"Mingyang Chen","status":"claimed_verified","statusLastChangedAt":"2025-09-03T08:31:47.108Z","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3da3","user":{"_id":"646c3ced3e2a7b06594bbaa4","avatarUrl":"/avatars/6e2d0e2f35e159a7832919a454583ab1.svg","isPro":false,"fullname":"李天鹏","user":"yuanshuai","type":"user"},"name":"Tianpeng Li","status":"claimed_verified","statusLastChangedAt":"2025-09-03T08:31:45.301Z","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3da4","user":{"_id":"6436bb0dd58a5ea528c55acb","avatarUrl":"/avatars/df17b66780e14e07bbe4625f068a94ad.svg","isPro":false,"fullname":"Alvin Sun","user":"AlvinSunYooo","type":"user"},"name":"Haoze Sun","status":"claimed_verified","statusLastChangedAt":"2025-05-15T10:41:04.653Z","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3da5","user":{"_id":"658670184f349f95cf7d2252","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/658670184f349f95cf7d2252/MfYwxDS1w2kIvav2GvE_U.jpeg","isPro":false,"fullname":"Jie","user":"Jayok6","type":"user"},"name":"Yijie Zhou","status":"claimed_verified","statusLastChangedAt":"2025-09-03T08:31:40.752Z","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3da6","name":"Chenzheng Zhu","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3da7","user":{"_id":"641c45c921964f8f6d451d16","avatarUrl":"/avatars/da06cc603f8f9ee46ddb7dc72aae5bec.svg","isPro":false,"fullname":"FanYang","user":"fairyang","type":"user"},"name":"Fan Yang","status":"claimed_verified","statusLastChangedAt":"2025-09-03T08:31:43.334Z","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3da8","name":"Zenan Zhou","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3da9","name":"Weipeng Chen","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3daa","name":"Haofen Wang","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3dab","name":"Jeff Z. Pan","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3dac","name":"Wen Zhang","hidden":false},{"_id":"67e365b0dcfc2aeae1bf3dad","name":"Huajun Chen","hidden":false}],"publishedAt":"2025-03-25T09:00:58.000Z","submittedOnDailyAt":"2025-03-26T00:56:07.098Z","title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement\n Learning","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"Large Language Models (LLMs) have shown remarkable capabilities in reasoning,\nexemplified by the success of OpenAI-o1 and DeepSeek-R1. However, integrating\nreasoning with external search processes remains challenging, especially for\ncomplex multi-hop questions requiring multiple retrieval steps. We propose\nReSearch, a novel framework that trains LLMs to Reason with Search via\nreinforcement learning without using any supervised data on reasoning steps.\nOur approach treats search operations as integral components of the reasoning\nchain, where when and how to perform searches is guided by text-based thinking,\nand search results subsequently influence further reasoning. We train ReSearch\non Qwen2.5-7B(-Instruct) and Qwen2.5-32B(-Instruct) models and conduct\nextensive experiments. Despite being trained on only one dataset, our models\ndemonstrate strong generalizability across various benchmarks. Analysis reveals\nthat ReSearch naturally elicits advanced reasoning capabilities such as\nreflection and self-correction during the reinforcement learning process.","upvotes":19,"discussionId":"67e365b1dcfc2aeae1bf3df6","githubRepo":"https://github.com/agent-rl/research","githubRepoAddedBy":"auto","ai_summary":"ReSearch is a framework that trains LLMs to integrate reasoning with search using reinforcement learning, enhancing capabilities for complex multi-hop questions.","ai_keywords":["Large Language Models","LLMs","OpenAI-o1","DeepSeek-R1","ReSearch","reinforcement learning","Qwen2.5-7B","Qwen2.5-32B"],"githubStars":1323},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"6434b6619bd5a84b5dcfa4de","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6434b6619bd5a84b5dcfa4de/h8Q6kPNjFNc03wmdboHzq.jpeg","isPro":true,"fullname":"Young-Jun Lee","user":"passing2961","type":"user"},{"_id":"6682ec8e9e8f301884217372","avatarUrl":"/avatars/65acb4e0c2e7328b27d75b18d0927444.svg","isPro":false,"fullname":"Zixiang Zheng","user":"imzhengzx","type":"user"},{"_id":"63082bb7bc0a2a5ee2253523","avatarUrl":"/avatars/6cf8d12d16d15db1070fbea89b5b3967.svg","isPro":false,"fullname":"Kuo-Hsin Tu","user":"dapumptu","type":"user"},{"_id":"60078446e55258e41786a959","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60078446e55258e41786a959/UGPCE4YqG9BVMSf0YauxL.png","isPro":false,"fullname":"Motoki Wu","user":"tokestermw","type":"user"},{"_id":"67cb764be34bbc71815b8c40","avatarUrl":"/avatars/e76a1bbbefd2d2c98c36f16f93ec8489.svg","isPro":false,"fullname":"Naveen Nallamothu","user":"naveennallamothu","type":"user"},{"_id":"651c80a26ba9ab9b9582c273","avatarUrl":"/avatars/e963452eafd21f517d800f2e58e0f918.svg","isPro":false,"fullname":"siyeng feng","user":"siyengfeng","type":"user"},{"_id":"5fd5e18a90b6dc4633f6d292","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/gZXHW5dd9R86AV9LMZ--y.png","isPro":true,"fullname":"Maziyar Panahi","user":"MaziyarPanahi","type":"user"},{"_id":"662dd7af9e6d371ab71cfd46","avatarUrl":"/avatars/9b99a47760715d41f54169620b782d5a.svg","isPro":false,"fullname":"Chao","user":"Youuxi","type":"user"},{"_id":"67e265f0c3cc4e5bab76c2bf","avatarUrl":"/avatars/a894885136a665ac5258b834c52558cc.svg","isPro":false,"fullname":"Agent-RL","user":"agentrl","type":"user"},{"_id":"602451620b002b9ff74df440","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/602451620b002b9ff74df440/Wrg8-_gJmwqVTT7c74-wD.png","isPro":false,"fullname":"Seth L","user":"splevine","type":"user"},{"_id":"6254f8e5d21e4cc386b881ad","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1649899774659-6254f8e5d21e4cc386b881ad.jpeg","isPro":false,"fullname":"Somshubra Majumdar","user":"smajumdar94","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">