{"id":6311,"date":"2025-02-26T04:24:00","date_gmt":"2025-02-25T19:24:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6311"},"modified":"2025-02-26T04:24:00","modified_gmt":"2025-02-25T19:24:00","slug":"revisiting-the-test-time-scaling-of-o1-like-models-do-they-truly-possess-test-time-scaling-capabilities","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6311","title":{"rendered":"Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?\u00a0<\/strong>[61.9]<br>\u6211\u3005\u306f,o1-like large language model (LLMs) \u304c\u672c\u5f53\u306b\u30c6\u30b9\u30c8\u6642\u9593\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u6a5f\u80fd\u3092\u6301\u3063\u3066\u3044\u308b\u304b\u691c\u8a0e\u3057\u305f\u3002 \u3053\u308c\u3089\u306eo1\u578b\u30e2\u30c7\u30eb\u306e\u9577\u3044CoT\u306f\u3001\u5e38\u306b\u7cbe\u5ea6\u3092\u5411\u4e0a\u3057\u306a\u3044\u3053\u3068\u304c\u308f\u304b\u3063\u305f\u3002 \u4e26\u5217\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u6226\u7565\u3068CoT\u9577\u7279\u6027\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u624b\u6cd5\u3067\u3042\u308bShortest Majority Vote\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2502.12215v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2502.12215v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 17 Feb 2025 07:21:11 GMT)<\/li>\n\n\n\n<li>\u5fc5\u305a\u9577\u3044\u63a8\u8ad6\u304c\u6027\u80fd\u5411\u4e0a\u306b\u3064\u306a\u304c\u3063\u3066\u304a\u3089\u305a\u300cThese results reveal that self-revision ability is a key factor in the effectiveness of sequential scaling for o1-like models.\u300d\u3060\u3063\u305f\u3068\u306e\u3053\u3068\u3002\u5b9f\u9a13\u7d50\u679c\u304b\u3089\u300cShortest Majority Vote, which incorporate parallel scaling approaches with our insight on sequential scaling.\u300d\u3092\u63d0\u6848\u3002<\/li>\n\n\n\n<li>\u524d\u534a\u306f<a href=\"https:\/\/devneko.jp\/wordpress\/?p=6243\">The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks \u2013 arXiv\u6700\u65b0\u8ad6\u6587\u306e\u7d39\u4ecb<\/a>\u3092\u601d\u3044\u3046\u304b\u3076\u3002\u63d0\u6848\u624b\u6cd5\u306e\u518d\u73fe\u5b9f\u9a13\u306a\u3069\u304c\u6c17\u306b\u306a\u308b\u3068\u3053\u308d\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":[],"class_list":["post-6311","post","type-post","status-publish","format-standard","hentry","category-arxiv"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6311","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=6311"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6311\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6311"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6311"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6311"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}