{"id":6824,"date":"2025-05-27T04:58:00","date_gmt":"2025-05-26T19:58:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6824"},"modified":"2025-05-25T10:02:29","modified_gmt":"2025-05-25T01:02:29","slug":"gui-explorer-autonomous-exploration-and-mining-of-transition-aware-knowledge-for-gui-agent","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6824","title":{"rendered":"GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent\u00a0<\/strong>[66.3]<br>MLLM\u306fUI\u30b3\u30f3\u30dd\u30fc\u30cd\u30f3\u30c8\u306e\u8aa4\u89e3\u91c8\u3068\u53e4\u3044\u77e5\u8b58\u306e2\u3064\u306e\u5927\u304d\u306a\u554f\u984c\u306b\u60a9\u307e\u3055\u308c\u3066\u3044\u308b\u3002 \u672c\u7a3f\u3067\u306f,2\u3064\u306e\u57fa\u672c\u7684\u306a\u30e1\u30ab\u30cb\u30ba\u30e0\u3092\u7d44\u307f\u8fbc\u3093\u3060\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u4e0d\u8981\u306aGUI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3067\u3042\u308bGUI-Explorer\u3092\u63d0\u6848\u3059\u308b\u3002 SPA-Bench\u3067\u306f53.7%\u3001AndroidWorld\u3067\u306f47.4%\u306e\u30bf\u30b9\u30af\u6210\u529f\u7387\u3067\u3001GUI-Explorer\u306fSOTA\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3088\u308a\u3082\u5927\u5e45\u306b\u6539\u5584\u3055\u308c\u3066\u3044\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2505.16827v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2505.16827v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 22 May 2025 16:01:06 GMT)<\/li>\n\n\n\n<li>\u300c(a) Automatically constructing function-aware exploration goals by analyzing structural information from the GUI environment, followed by systematic exploration to collect diverse function- aware trajectories. (b) Extracting effective screen-operation logic through unsupervised analysis of structured interaction triples (observation, action, outcome), enabling unsupervised knowledge extraction. (c) Performing visual-semantic retrieval between screen visuals and the knowledge vector store to construct Dynamic Guidance achieves dual objectives: preventing UI misinterpretation and ensuring action proposals align with actual UI states.\u300d\u3068\u3044\u3046\u30e1\u30ab\u30cb\u30ba\u30e0\u306e\u63d0\u6848\u3002SPA-Bench\u3001AndroidWorld\u306e\u30b9\u30b3\u30a2\u3092\u6539\u5584\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/JiuTian-VL\/GUI-explorer\">GitHub &#8211; JiuTian-VL\/GUI-explorer: [ACL 2025] GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent<\/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":[181],"class_list":["post-6824","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-gui-agent"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6824","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=6824"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6824\/revisions"}],"predecessor-version":[{"id":6825,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6824\/revisions\/6825"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6824"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6824"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6824"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}