{"id":6050,"date":"2025-01-14T03:38:00","date_gmt":"2025-01-13T18:38:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6050"},"modified":"2025-01-14T03:38:00","modified_gmt":"2025-01-13T18:38:00","slug":"rstar-math-small-llms-can-master-math-reasoning-with-self-evolved-deep-thinking","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6050","title":{"rendered":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking\u00a0<\/strong>[15.4]<br>\u672c\u7a3f\u3067\u306f,\u5c0f\u578b\u8a00\u8a9e\u30e2\u30c7\u30eb (SLM) \u304c OpenAI o1 \u306e\u7b97\u8853\u7684\u63a8\u8ad6\u80fd\u529b\u306b\u5339\u6575\u3059\u308b\u304b,\u8d85\u8d8a\u3059\u308b\u304b\u3092\u793a\u3059\u305f\u3081\u306b rStar-Math \u3092\u63d0\u6848\u3059\u308b\u3002 \u6211\u3005\u306f\u30e2\u30f3\u30c6\u30ab\u30eb\u30ed\u6728\u63a2\u7d22(MCTS)\u3092\u901a\u3057\u3066\u300c\u6df1\u5c64\u601d\u8003\u300d\u3092\u5b9f\u8df5\u3057,SLM\u306b\u57fa\u3065\u304f\u30d7\u30ed\u30bb\u30b9\u5831\u916c\u30e2\u30c7\u30eb\u306b\u3088\u308b\u30c6\u30b9\u30c8\u6642\u9593\u63a2\u7d22\u3092\u884c\u3046\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2501.04519v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2501.04519v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 08 Jan 2025 14:12:57 GMT)<\/li>\n\n\n\n<li>\u300cIn this work, we present rStar-Math, a self-evolved System 2 deep thinking approach that significantly boosts the math reasoning capabilities of small LLMs, achieving state-of-the-art OpenAI o1-level performance.\u300d\u3068\u6d41\u884c\u308a\u306e\u30a2\u30d7\u30ed\u30fc\u30c1\u3001self-evolved\u3068\u3044\u3046\u8868\u73fe\u306b\u672a\u6765\u3092\u611f\u3058\u308b\u3068\u3068\u3082\u306b\u3001\u6bd4\u8f03\u7684\u5c0f\u898f\u6a21\u306a\u30e2\u30c7\u30eb\u3067\u3082\u9ad8\u3044\u30b9\u30b3\u30a2\u3092\u3068\u308c\u3066\u3044\u308b\u3053\u3068\u304c\u8208\u5473\u6df1\u3044<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/microsoft\/rStar\">https:\/\/github.com\/microsoft\/rStar<\/a>\u3002\u73fe\u6642\u70b9\u3067\u306f404\uff1f<\/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":[232,283,365,366],"class_list":["post-6050","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-lrm","tag-o1","tag-slm","tag-slow-thinking"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6050","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=6050"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6050\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6050"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6050"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6050"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}