{"id":8273,"date":"2026-03-12T05:49:00","date_gmt":"2026-03-11T20:49:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=8273"},"modified":"2026-03-07T15:39:55","modified_gmt":"2026-03-07T06:39:55","slug":"omnigaia-towards-native-omni-modal-ai-agents","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=8273","title":{"rendered":"OmniGAIA: Towards Native Omni-Modal AI Agents"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>OmniGAIA: Towards Native Omni-Modal AI Agents\u00a0<\/strong>[103.8]<br>\u6211\u3005\u306f\u3001\u6df1\u3044\u63a8\u8ad6\u3068\u30de\u30eb\u30c1\u30bf\u30fc\u30f3\u30c4\u30fc\u30eb\u306e\u5b9f\u884c\u3092\u5fc5\u8981\u3068\u3059\u308b\u30bf\u30b9\u30af\u306b\u304a\u3044\u3066\u3001\u30aa\u30e0\u30cb\u30e2\u30fc\u30c0\u30eb\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3092\u8a55\u4fa1\u3059\u308b\u305f\u3081\u306b\u8a2d\u8a08\u3055\u308c\u305f\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3092\u5c0e\u5165\u3059\u308b\u3002 \u6211\u3005\u306f,Omni-modal foundation agent\u3067\u3042\u308bOmniAtlas\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2602.22897v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2602.22897v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 26 Feb 2026 11:35:04 GMT)<\/li>\n\n\n\n<li>\u300cOmniGAIA, a challenging benchmark for native omni-modal agents. OmniGAIA comprises 360 tasks across 9 real-world domains, covering both video-with-audio and image+audio settings, and explicitly requires multi-turn tool use (e g , web search\/browsing and code) to produce verifiable open-form answers.\u300d\u3068\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u306a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002\u30c7\u30e2\u304c\u5206\u304b\u308a\u3084\u3059\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/RUC-NLPIR\/OmniGAIA\">GitHub &#8211; RUC-NLPIR\/OmniGAIA: OmniGAIA: Towards Native Omni-Modal AI Agents<\/a>\u3001\u30ea\u30fc\u30c0\u30fc\u30dc\u30fc\u30c9\u306f<a href=\"https:\/\/huggingface.co\/spaces\/RUC-NLPIR\/OmniGAIA-Leaderboard\">OmniGAIA Leaderboard &#8211; a Hugging Face Space by RUC-NLPIR<\/a>\u3001\u5546\u7528\u30e2\u30c7\u30eb\uff08Gemini\uff09\u306e\u5f37\u3055\u304c\u76ee\u7acb\u3064<\/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":[517,524],"class_list":["post-8273","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-517","tag-524"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8273","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=8273"}],"version-history":[{"count":2,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8273\/revisions"}],"predecessor-version":[{"id":8275,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/8273\/revisions\/8275"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8273"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8273"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8273"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}