{"id":5793,"date":"2024-11-26T05:09:00","date_gmt":"2024-11-25T20:09:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5793"},"modified":"2024-11-26T05:09:00","modified_gmt":"2024-11-25T20:09:00","slug":"marco-o1-towards-open-reasoning-models-for-open-ended-solutions","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5793","title":{"rendered":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions&nbsp;<\/strong>[40.2]<br>Marco-o1\u306f\u6570\u5b66\u3001\u7269\u7406\u5b66\u3001\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u306a\u3069\u306e\u6a19\u6e96\u89e3\u3092\u6301\u3064\u5206\u91ce\u306b\u7126\u70b9\u3092\u5f53\u3066\u3066\u3044\u308b\u3002 o1\u30e2\u30c7\u30eb\u306f\u3001\u660e\u78ba\u306a\u6a19\u6e96\u304c\u6b20\u5982\u3057\u3001\u5831\u916c\u304c\u5b9a\u91cf\u5316\u304c\u96e3\u3057\u3044\u5e83\u3044\u9818\u57df\u306b\u52b9\u679c\u7684\u306b\u4e00\u822c\u5316\u3057\u307e\u3059\u304b? Marco-o1\u306f\u3001Chain-of-Thought\u30d5\u30a1\u30a4\u30f3\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u3001Monte Carlo Tree Search (MCTS)\u3001\u30ea\u30d5\u30ec\u30af\u30b7\u30e7\u30f3\u30e1\u30ab\u30cb\u30ba\u30e0\u3001\u9769\u65b0\u7684\u306a\u63a8\u8ad6\u6226\u7565\u306b\u3088\u3063\u3066\u5b9f\u73fe\u3055\u308c\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2411.14405v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2411.14405v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Thu, 21 Nov 2024 18:37:33 GMT)<\/li>\n\n\n\n<li>\u300cOur Marco-o1 enhances the reasoning ability by integrating Chain-of-Thought (CoT) fine-tuning, Monte Carlo Tree Search (MCTS), and novel reasoning action strategies.\u300d\u3068\u3044\u3046o1\u30e9\u30a4\u30af\u306a\u30e2\u30c7\u30eb\u69cb\u7bc9\u306b\u95a2\u3059\u308b\u5831\u544a\u3002<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective\u00a0<\/strong>[77.9]<br>OpenAI\u306f\u3001o1\u306e\u80cc\u5f8c\u306b\u3042\u308b\u4e3b\u8981\u306a\u6280\u8853\u306f\u5f37\u5316\u5b66\u7fd2\u3067\u3042\u308b\u3068\u4e3b\u5f35\u3057\u3066\u3044\u308b\u3002 \u672c\u7a3f\u3067\u306f\u3001\u5f37\u5316\u5b66\u7fd2\u306e\u89b3\u70b9\u304b\u3089\u3001o1\u3092\u9054\u6210\u3059\u308b\u305f\u3081\u306e\u30ed\u30fc\u30c9\u30de\u30c3\u30d7\u3092\u5206\u6790\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2412.14135v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2412.14135v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 18 Dec 2024 18:24:47 GMT)<\/li>\n\n\n\n<li>\u300cIn this paper, we present a roadmap for reproducing o1 from the perspective of reinforcement learning, emphasizing key components such as policy initialization, reward design, search, and learning.\u300d\u3068\u3044\u3046\u8ad6\u6587\u3082\u3002<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[232,283],"class_list":["post-5793","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-lrm","tag-o1"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5793","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=5793"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5793\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5793"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5793"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5793"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}