{"id":6066,"date":"2025-01-20T04:26:00","date_gmt":"2025-01-19T19:26:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6066"},"modified":"2025-01-20T04:26:00","modified_gmt":"2025-01-19T19:26:00","slug":"multiagent-finetuning-self-improvement-with-diverse-reasoning-chains","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6066","title":{"rendered":"Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains\u00a0<\/strong>[114.8]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306f\u8fd1\u5e74\u9855\u8457\u306a\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u9054\u6210\u3057\u3066\u3044\u308b\u304c\u3001\u57fa\u790e\u3068\u306a\u308b\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30c7\u30fc\u30bf\u306b\u3088\u3063\u3066\u6839\u672c\u7684\u306b\u5236\u9650\u3055\u308c\u3066\u3044\u308b\u3002 \u672c\u7a3f\u3067\u306f,\u8a00\u8a9e\u30e2\u30c7\u30eb\u306e\u30de\u30eb\u30c1\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u793e\u4f1a\u306b\u30d5\u30a1\u30a4\u30f3\u30bf\u30cb\u30f3\u30b0\u3092\u9069\u7528\u3057\u305f\u81ea\u5df1\u6539\u5584\u3078\u306e\u88dc\u5b8c\u7684\u30a2\u30d7\u30ed\u30fc\u30c1\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2501.05707v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2501.05707v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 10 Jan 2025 04:35:46 GMT)<\/li>\n\n\n\n<li>\u300cInstead of fine-tuning a single model, our method finetunes a multiagent set of language models from the same base model and then independently specializes each model to capture parts of a task of interest.\u300d\u3068\u3044\u3046\u81ea\u5df1\u6539\u5584\u30a2\u30d7\u30ed\u30fc\u30c1\u306e\u63d0\u6848\u3002Generation Model\u3068Critic Model\u3092\u540c\u6642\u306b\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u3057\u3066\u3044\u304d\u3001\u30de\u30eb\u30c1\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306a\u30c7\u30a3\u30d9\u30fc\u30c8\u3092\u901a\u3057\u3066\u7d71\u5408\u3068\u3044\u3046\u52d5\u304d\u3002Critic model\u306e\u91cd\u8981\u6027\u3082\u9ad8\u305d\u3046\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/llm-multiagent-ft.github.io\/\">Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains<\/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":[84,356],"class_list":["post-6066","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-critic","tag-self-x"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6066","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=6066"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6066\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6066"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6066"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6066"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}