{"id":3896,"date":"2023-10-10T05:47:00","date_gmt":"2023-10-09T20:47:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=3896"},"modified":"2023-10-10T05:47:00","modified_gmt":"2023-10-09T20:47:00","slug":"benchmarking-large-language-models-as-ai-research-agents","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=3896","title":{"rendered":"Benchmarking Large Language Models As AI Research Agents"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Benchmarking Large Language Models As AI Research Agents\u00a0<\/strong>[105.7]<br>\u6211\u3005\u306f,AI\u7814\u7a76\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3092\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3059\u308bML\u30bf\u30b9\u30af\u30b9\u30a4\u30fc\u30c8\u3067\u3042\u308bMLAgentBench\u3092\u63d0\u6848\u3059\u308b\u3002 \u6211\u3005\u306f, GPT-4\u3092\u30d9\u30fc\u30b9\u3068\u3057\u305f\u7814\u7a76\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u304c, MLAgentBench\u306e\u591a\u304f\u306e\u30bf\u30b9\u30af\u306b\u304a\u3044\u3066, \u9b45\u529b\u7684\u306aML\u30e2\u30c7\u30eb\u3092\u69cb\u7bc9\u3067\u304d\u308b\u3053\u3068\u3092\u767a\u898b\u3057\u305f\u3002 \u9577\u671f\u8a08\u753b\u3084\u5e7b\u899a\u306a\u3069,LLM\u3092\u30d9\u30fc\u30b9\u3068\u3057\u305f\u7814\u7a76\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306b\u3068\u3063\u3066\u91cd\u8981\u306a\u8ab2\u984c\u3092\u3044\u304f\u3064\u304b\u6319\u3052\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2310.03302v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2310.03302v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 5 Oct 2023 04:06:12 GMT)<\/li>\n\n\n\n<li>\u30c7\u30fc\u30bf\u51e6\u7406\u3001\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u9078\u629e\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30d7\u30ed\u30bb\u30b9\u306a\u3069\u3001\u6a5f\u68b0\u5b66\u7fd2\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u5168\u4f53\u3092\u5bfe\u8c61\u3068\u3059\u308b\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u7528\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002\u30bf\u30b9\u30af\u306f\u826f\u304f\u7814\u7a76\u3055\u308c\u3066\u3044\u308b\u3082\u306eKaggle\u306b\u3042\u308b\u3082\u306e\u6700\u8fd1\u306e\u30bf\u30b9\u30af\u306a\u3069\u69d8\u3005\u3002\u7d50\u679c\u3082GPT-4\u306f\u512a\u308c\u3066\u3044\u308b\u3082\u306e\u306e\u30bf\u30b9\u30af\u9593\u306e\u5dee\u7570\u304c\u5927\u304d\u3044\u3088\u3046\u306b\u898b\u3048\u308b\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/snap-stanford\/MLAgentBench\">GitHub &#8211; snap-stanford\/MLAgentBench<\/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":[42,223,517],"class_list":["post-3896","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent","tag-llm","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3896","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=3896"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/3896\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3896"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3896"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3896"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}