{"id":7340,"date":"2025-08-25T05:33:00","date_gmt":"2025-08-24T20:33:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7340"},"modified":"2026-01-11T07:54:19","modified_gmt":"2026-01-10T22:54:19","slug":"futurex-an-advanced-live-benchmark-for-llm-agents-in-future-prediction","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7340","title":{"rendered":"FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction\u00a0<\/strong>[84.4]<br>FutureX\u306f\u3001\u5c06\u6765\u306e\u4e88\u6e2c\u306e\u305f\u3081\u306e\u6700\u5927\u304b\u3064\u6700\u3082\u591a\u69d8\u306a\u30e9\u30a4\u30d6\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308b\u3002 \u30ea\u30a2\u30eb\u30bf\u30a4\u30e0\u306e\u65e5\u6b21\u66f4\u65b0\u3092\u30b5\u30dd\u30fc\u30c8\u3057\u3001\u8cea\u554f\u53ce\u96c6\u3068\u56de\u7b54\u53ce\u96c6\u306e\u305f\u3081\u306e\u81ea\u52d5\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u3092\u901a\u3058\u3066\u30c7\u30fc\u30bf\u306e\u6c5a\u67d3\u3092\u53d6\u308a\u9664\u304f\u3002 \u63a8\u8ad6,\u691c\u7d22\u6a5f\u80fd,\u5916\u90e8\u30c4\u30fc\u30eb\u306e\u7d71\u5408\u306a\u3069\u3092\u542b\u308025\u306eLLM\/\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30e2\u30c7\u30eb\u3092\u8a55\u4fa1\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2508.11987v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2508.11987v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Sat, 16 Aug 2025 08:54:08 GMT)<\/li>\n\n\n\n<li>\u672a\u6765\u4e88\u6e2c\u306e\u305f\u3081\u306e\u30e9\u30a4\u30d6\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002\u300cwe introduce FutureX, a dynamic and live evaluation benchmark specifically designed for LLM agents performing future prediction tasks. FutureX is built upon a semi-automated pipeline that continuously collects future-oriented questions from 195 diverse websites, curated from a pool of 2,008 sites covering areas such as politics, economics, technology, sports, healthcare, and more.\u300d\u3068\u30c9\u30e1\u30a4\u30f3\u3082\u5e83\u3044\u3002<\/li>\n\n\n\n<li>\u7d50\u679c\u3068\u3057\u3066\u300cLLM agents still lag behind humans\u300d\u3067\u306f\u3042\u308b\u3082\u306e\u306e\u3001\u30ec\u30d9\u30eb\uff12\u306f\u4eba\u3092\u4e0a\u56de\u3063\u3066\u3044\u308b\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u304c\u3044\u308b\u306e\u304c\u8208\u5473\u6df1\u3044\u3068\u3053\u308d\u3002\uff08\u3042\u3068\u30ec\u30d9\u30eb\u5206\u3051\u306f\u82e5\u5e72\u9055\u548c\u611f\u304c\u3042\u308b\u3002\u3002\u3002\uff09\n<ul class=\"wp-block-list\">\n<li>The Basic tier (Level 1) contains single-choice events with options fewer than 4.<\/li>\n\n\n\n<li>The Wide Search tier (Level 2) comprises multi-choice events with several correct answers.<\/li>\n\n\n\n<li>\u00a0The Deep Search tier (Level 3) contains open-ended events whose underlying facts are relatively stable (with low volatility).<\/li>\n\n\n\n<li>The Super Agent tier (Level4) covers high-volatility, open-ended events.<\/li>\n<\/ul>\n<\/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":[712,517],"class_list":["post-7340","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-foresight","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7340","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=7340"}],"version-history":[{"count":2,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7340\/revisions"}],"predecessor-version":[{"id":7342,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7340\/revisions\/7342"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7340"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7340"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7340"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}