{"id":6082,"date":"2025-01-27T03:35:00","date_gmt":"2025-01-26T18:35:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6082"},"modified":"2025-01-27T03:35:00","modified_gmt":"2025-01-26T18:35:00","slug":"towards-large-reasoning-models-a-survey-of-reinforced-reasoning-with-large-language-models","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6082","title":{"rendered":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models\u00a0<\/strong>[33.1]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306f\u3001\u8907\u96d1\u306a\u63a8\u8ad6\u30bf\u30b9\u30af\u306b\u5bfe\u51e6\u3059\u308b\u305f\u3081\u306b\u305d\u308c\u3089\u3092\u6d3b\u7528\u3059\u308b\u3053\u3068\u306b\u5927\u304d\u306a\u7814\u7a76\u306e\u95a2\u5fc3\u3092\u547c\u3093\u3060\u3002 \u6700\u8fd1\u306e\u7814\u7a76\u306f\u3001LLM\u304c\u30c6\u30b9\u30c8\u6642\u9593\u63a8\u8ad6\u4e2d\u306b\u3088\u308a\u591a\u304f\u306e\u30c8\u30fc\u30af\u30f3\u3067&#8221;\u8003\u3048\u308b&#8221;\u3053\u3068\u3092\u5968\u52b1\u3059\u308b\u3053\u3068\u306f\u3001\u63a8\u8ad6\u306e\u7cbe\u5ea6\u3092\u8457\u3057\u304f\u5411\u4e0a\u3055\u305b\u308b\u3053\u3068\u3092\u793a\u3057\u305f\u3002 OpenAI\u306eo1\u30b7\u30ea\u30fc\u30ba\u306e\u5c0e\u5165\u306f\u3001\u3053\u306e\u7814\u7a76\u306e\u65b9\u5411\u6027\u306b\u304a\u3044\u3066\u91cd\u8981\u306a\u30de\u30a4\u30eb\u30b9\u30c8\u30fc\u30f3\u3067\u3042\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2501.09686v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2501.09686v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 16 Jan 2025 17:37:58 GMT)<\/li>\n\n\n\n<li>OpenAI o1\u30e9\u30a4\u30af\u306a\u30e2\u30c7\u30eb\u3001Large Reasoning Models\u306e\u30b5\u30fc\u30d9\u30a4\u3002\u300cWe begin by introducing the foundational background of LLMs and then explore the key technical components driving the development of large reasoning models, with a focus on automated data construction, learning-to-reason techniques, and test-time scaling.\u300d\u3068\u3042\u308b\u901a\u308a\u5305\u62ec\u7684\u306a\u5185\u5bb9\u3002<\/li>\n\n\n\n<li>\u4e0b\u8a18\u3067\u3082\u601d\u3063\u305f\u304c\u672c\u5f53\u306b\u9032\u5c55\u304c\u901f\u3044<\/li>\n<\/ul>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>O1 Replication Journey &#8212; Part 3: Inference-time Scaling for Medical Reasoning\u00a0<\/strong>[27.8]<br>\u3053\u306e\u7814\u7a76\u306f\u3001\u533b\u5b66\u7684\u63a8\u8ad6\u30bf\u30b9\u30af\u306e\u305f\u3081\u306e\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306b\u304a\u3051\u308b\u63a8\u8ad6\u6642\u9593\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u306e\u53ef\u80fd\u6027\u3092\u63a2\u308b\u3082\u306e\u3067\u3042\u308b\u3002 500\u30b5\u30f3\u30d7\u30eb\u3092\u9069\u5ea6\u306b\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3059\u308b\u3053\u3068\u3067,\u672c\u30e2\u30c7\u30eb\u3067\u306f6%-11%\u306e\u6027\u80fd\u5411\u4e0a\u3092\u5b9f\u73fe\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2501.06458v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2501.06458v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sat, 11 Jan 2025 07:10:23 GMT)<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/github.com\/SPIRAL-MED\/Ophiuchus\">GitHub &#8211; SPIRAL-MED\/Ophiuchus<\/a><\/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":[232,283,387],"class_list":["post-6082","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-lrm","tag-o1","tag-survey"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6082","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=6082"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6082\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6082"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6082"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6082"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}