{"id":6946,"date":"2025-06-19T06:03:00","date_gmt":"2025-06-18T21:03:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6946"},"modified":"2025-06-15T21:08:39","modified_gmt":"2025-06-15T12:08:39","slug":"mirage-1-augmenting-and-updating-gui-agent-with-hierarchical-multimodal-skills","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6946","title":{"rendered":"Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills\u00a0<\/strong>[57.7]<br>\u672c\u7a3f\u3067\u306f,\u77e5\u8b58\u4e0d\u8db3\u306e\u554f\u984c\u306b\u5bfe\u51e6\u3059\u308b\u305f\u3081,\u968e\u5c64\u578b\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30b9\u30ad\u30eb(HMS)\u30e2\u30b8\u30e5\u30fc\u30eb\u3092\u63d0\u6848\u3059\u308b\u3002 \u30c8\u30e9\u30b8\u30a7\u30af\u30c8\u30ea\u3092\u5b9f\u884c\u30b9\u30ad\u30eb\u3001\u30b3\u30a2\u30b9\u30ad\u30eb\u3001\u305d\u3057\u3066\u6700\u7d42\u7684\u306b\u306f\u30e1\u30bf\u30b9\u30ad\u30eb\u306b\u5f90\u3005\u306b\u62bd\u8c61\u5316\u3057\u3001\u9577\u671f\u306e\u30bf\u30b9\u30af\u8a08\u753b\u306e\u305f\u3081\u306e\u968e\u5c64\u7684\u306a\u77e5\u8b58\u69cb\u9020\u3092\u63d0\u4f9b\u3059\u308b\u3002 \u30c9\u30e1\u30a4\u30f3\u30ae\u30e3\u30c3\u30d7\u3092\u57cb\u3081\u308b\u305f\u3081\u306b,Skill-Augmented Monte Carlo Tree Search (SA-MCTS)\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2506.10387v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2506.10387v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 12 Jun 2025 06:21:19 GMT)<\/li>\n\n\n\n<li>\u300cHierarchical Multimodal Skills (HMS) module for long-horizon planning\u300d\u3001\u300cA Skill-Augmented Monte Carlo Tree Search (SA-MCTS) algorithm for knowledge exploration in online settings.\u300d\u3092\u30ad\u30fc\u3068\u3059\u308bcross-platform, plug-and-play GUI agent\u3001Mirage-1\u306e\u63d0\u6848<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/cybertronagent.github.io\/Mirage-1.github.io\/\">Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills<\/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":[42,181],"class_list":["post-6946","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent","tag-gui-agent"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6946","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=6946"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6946\/revisions"}],"predecessor-version":[{"id":6947,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6946\/revisions\/6947"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6946"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6946"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6946"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}