{"id":5194,"date":"2024-07-24T03:24:00","date_gmt":"2024-07-23T18:24:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=5194"},"modified":"2024-07-24T03:24:00","modified_gmt":"2024-07-23T18:24:00","slug":"spider2-v-how-far-are-multimodal-agents-from-automating-data-science-and-engineering-workflows","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=5194","title":{"rendered":"Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?\u00a0<\/strong>[73.8]<br>\u6211\u3005\u306f\u3001\u30d7\u30ed\u306e\u30c7\u30fc\u30bf\u30b5\u30a4\u30a8\u30f3\u30b9\u3068\u30a8\u30f3\u30b8\u30cb\u30a2\u30ea\u30f3\u30b0\u306b\u7126\u70b9\u3092\u5f53\u3066\u305f\u6700\u521d\u306e\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308bSpider2-V\u3092\u7d39\u4ecb\u3059\u308b\u3002 Spider2-V\u306f\u3001\u672c\u7269\u306e\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u74b0\u5883\u306b\u304a\u3051\u308b\u73fe\u5b9f\u4e16\u754c\u306e\u30bf\u30b9\u30af\u3092\u7279\u5fb4\u3068\u3057\u300120\u306e\u30a8\u30f3\u30bf\u30fc\u30d7\u30e9\u30a4\u30ba\u30ec\u30d9\u30eb\u306e\u30d7\u30ed\u30d5\u30a7\u30c3\u30b7\u30e7\u30ca\u30eb\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u3092\u7d44\u307f\u8fbc\u3093\u3067\u3044\u308b\u3002 \u3053\u308c\u3089\u306e\u30bf\u30b9\u30af\u306f\u3001\u30a8\u30f3\u30bf\u30fc\u30d7\u30e9\u30a4\u30ba\u30c7\u30fc\u30bf\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u30b7\u30b9\u30c6\u30e0\u306b\u304a\u3044\u3066\u3001\u30b3\u30fc\u30c9\u3092\u66f8\u304d\u3001GUI\u3092\u7ba1\u7406\u3059\u308b\u3053\u3068\u3067\u3001\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u304c\u30c7\u30fc\u30bf\u95a2\u9023\u306e\u30bf\u30b9\u30af\u3092\u5b9f\u884c\u3059\u308b\u80fd\u529b\u3092\u8a55\u4fa1\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2407.10956v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2407.10956v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 15 Jul 2024 17:54:37 GMT)<\/li>\n\n\n\n<li>\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306e\u305f\u3081\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3001\u5bfe\u8c61\u30bf\u30b9\u30af\u306f\u300c494 real-world tasks across the complete data science and engineering workflows (from data warehousing to orchestration)\u300d\u3068\u3053\u308c\u304c\u81ea\u52d5\u5316\u3055\u308c\u308b\u3068\u5f71\u97ff\u306f\u5c11\u306a\u304f\u306a\u3055\u305d\u3046\uff08\u305f\u3060\u3057AutoML\u306a\u3069\u904e\u53bb\u304b\u3089\u81ea\u52d5\u5316\u3092\u76ee\u6307\u3057\u3066\u304d\u305f\u696d\u52d9\u3067\u306f\u3042\u308b\uff09<\/li>\n\n\n\n<li>\u300cThe most advanced VLM (GPT-4V) still performs poorly on Spider2-V (achieving 14.0% success rate), rendering it a very challenging benchmark.\u300d\u3068\u6700\u65b0\u30e2\u30c7\u30eb\u3067\u3082\u30b9\u30b3\u30a2\u306f\u304b\u306a\u308a\u60aa\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/spider2-v.github.io\/\">Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?<\/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":[42,251,517],"class_list":["post-5194","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent","tag-mllm","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5194","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=5194"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/5194\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=5194"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=5194"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=5194"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}