{"id":5120,"date":"2024-07-18T05:03:00","date_gmt":"2024-07-17T20:03:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5120"},"modified":"2024-07-18T05:03:00","modified_gmt":"2024-07-17T20:03:00","slug":"mobile-bench-an-evaluation-benchmark-for-llm-based-mobile-agents","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5120","title":{"rendered":"Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents&nbsp;<\/strong>[46.8]<br>\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb(LLM)\u306f\u4eba\u9593\u3068\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u306e\u76f8\u4e92\u4f5c\u7528\u306b\u304a\u3044\u3066\u30db\u30c3\u30c8\u30b9\u30dd\u30c3\u30c8\u3068\u306a\u3063\u3066\u3044\u308b\u3002 Mobile-Bench\u306f\u3001LLM\u30d9\u30fc\u30b9\u306e\u30e2\u30d0\u30a4\u30eb\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306e\u80fd\u529b\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306e\u65b0\u3057\u3044\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2407.00993v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2407.00993v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Mon, 01 Jul 2024 06:10:01 GMT)<\/li>\n\n\n\n<li>\u30e2\u30d0\u30a4\u30eb\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u5411\u3051\u30d9\u30f3\u30c1\u30de\u30fc\u30af<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/XiaoMi\/MobileBench\">https:\/\/github.com\/XiaoMi\/MobileBench<\/a>\u3068\u306e\u3053\u3068\uff08arXiv\u3078\u306e\u516c\u958b\u6642\u70b9\u3067\u306f404\uff09<\/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":[42,517],"class_list":["post-5120","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5120","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=5120"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5120\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5120"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5120"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5120"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}