{"id":5650,"date":"2024-10-21T05:43:00","date_gmt":"2024-10-20T20:43:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5650"},"modified":"2024-10-21T05:43:00","modified_gmt":"2024-10-20T20:43:00","slug":"agent-as-a-judge-evaluate-agents-with-agents","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5650","title":{"rendered":"Agent-as-a-Judge: Evaluate Agents with Agents"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Agent-as-a-Judge: Evaluate Agents with Agents\u00a0<\/strong>[61.3]<br>\u672c\u7a3f\u3067\u306f\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30fb\u30a2\u30ba\u30fb\u30a2\u30fb\u30b8\u30e3\u30c3\u30b8(Agent-as-a-Judge)\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3092\u7d39\u4ecb\u3057,\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30fb\u30b7\u30b9\u30c6\u30e0\u3092\u7528\u3044\u3066\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30fb\u30b7\u30b9\u30c6\u30e0\u306e\u8a55\u4fa1\u3092\u884c\u3046\u3002 \u3053\u308c\u306fLLM-as-a-Judge\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u306e\u6709\u6a5f\u7684\u62e1\u5f35\u3067\u3042\u308a\u3001\u30bf\u30b9\u30af\u89e3\u6c7a\u30d7\u30ed\u30bb\u30b9\u5168\u4f53\u306e\u4e2d\u9593\u30d5\u30a3\u30fc\u30c9\u30d0\u30c3\u30af\u3092\u53ef\u80fd\u306b\u3059\u308b\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u7684\u7279\u5fb4\u3092\u53d6\u308a\u5165\u308c\u3066\u3044\u308b\u3002 55\u306e\u30ea\u30a2\u30eb\u306a\u81ea\u52d5\u5316AI\u958b\u767a\u30bf\u30b9\u30af\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308bDevAI\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2410.10934v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2410.10934v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 14 Oct 2024 17:57:02 GMT)<\/li>\n\n\n\n<li>LLM-as-a-Judge\u306a\u3089\u306c\u3001Agent-as-a-Judge\u3002\u78ba\u304b\u306b\u6709\u52b9\u306a\u306e\u3060\u308d\u3046\u3068\u601d\u3046\u3002\u300cWe benchmark three of the popular agentic systems using Agent-as-a-Judge and find it dramatically outperforms LLM-as-a-Judge and is as reliable as our human evaluation baseline.\u300d\u3068\u306e\u3053\u3068\u3002<\/li>\n\n\n\n<li>\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u304c<a href=\"https:\/\/huggingface.co\/DEVAI-benchmark\">DEVAI-benchmark (DEVAI-benchmark)<\/a>\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\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":[224],"class_list":["post-5650","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-llm-as-a-judge"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5650","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=5650"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5650\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5650"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5650"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5650"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}