{"id":6652,"date":"2025-05-02T05:27:00","date_gmt":"2025-05-01T20:27:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6652"},"modified":"2025-05-02T05:27:00","modified_gmt":"2025-05-01T20:27:00","slug":"learning-adaptive-parallel-reasoning-with-language-models","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6652","title":{"rendered":"Learning Adaptive Parallel Reasoning with Language Models"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Learning Adaptive Parallel Reasoning with Language Models\u00a0<\/strong>[70.2]<br>\u672c\u7a3f\u3067\u306f,\u9069\u5fdc\u4e26\u5217\u63a8\u8ad6(Adaptive Parallel Reasoning, APR)\u3092\u63d0\u6848\u3059\u308b\u3002 APR\u306f\u3001spawn()\u3068join()\u64cd\u4f5c\u3092\u4f7f\u7528\u3057\u3066\u9069\u5fdc\u7684\u306a\u30de\u30eb\u30c1\u30b9\u30ec\u30c3\u30c9\u63a8\u8ad6\u3092\u53ef\u80fd\u306b\u3059\u308b\u3053\u3068\u3067\u3001\u65e2\u5b58\u306e\u63a8\u8ad6\u30e1\u30bd\u30c3\u30c9\u3092\u4e00\u822c\u5316\u3059\u308b\u3002 \u9375\u3068\u306a\u308b\u9769\u65b0\u306f\u3001\u89aa\u3068\u5b50\u306e\u4e21\u65b9\u306e\u63a8\u8ad6\u30b9\u30ec\u30c3\u30c9\u3092\u6700\u9069\u5316\u3057\u3066\u3001\u4e8b\u524d\u306b\u5b9a\u7fa9\u3055\u308c\u305f\u63a8\u8ad6\u69cb\u9020\u3092\u5fc5\u8981\u3068\u305b\u305a\u306b\u30bf\u30b9\u30af\u306e\u6210\u529f\u7387\u3092\u9ad8\u3081\u308b\u3001\u30a8\u30f3\u30c9\u30c4\u30fc\u30a8\u30f3\u30c9\u306e\u5f37\u5316\u5b66\u7fd2\u6226\u7565\u3067\u3042\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2504.15466v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2504.15466v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 21 Apr 2025 22:29:02 GMT)<\/li>\n\n\n\n<li>\u300cWe presented Adaptive Parallel Reasoning, which enables language models to adaptively distribute computation across serial and parallel reasoning paths using a parent-child threading mechanism.\u300d\u3068\u81ea\u7136\u8a00\u8a9e\u51e6\u7406\u3068\u3044\u3046\u3088\u308a\u3082\u63a2\u7d22\u306b\u8fd1\u3044\u306a\u30fc\u3068\u601d\u308f\u306a\u304f\u3082\u306a\u3044\u624b\u6cd5\u306e\u63d0\u6848\u3002\u6709\u52b9\u306a\u306e\u306f\u78ba\u304b\u3060\u3068\u601d\u3046\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/Parallel-Reasoning\/APR\">GitHub &#8211; Parallel-Reasoning\/APR: Code for Paper: Learning Adaptive Parallel Reasoning with Language Models<\/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":[366],"class_list":["post-6652","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-slow-thinking"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6652","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=6652"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6652\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6652"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6652"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6652"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}