{"id":7395,"date":"2025-09-16T06:28:00","date_gmt":"2025-09-15T21:28:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7395"},"modified":"2025-09-06T21:31:57","modified_gmt":"2025-09-06T12:31:57","slug":"flashadventure-a-benchmark-for-gui-agents-solving-full-story-arcs-in-diverse-adventure-games","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7395","title":{"rendered":"FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games\u00a0<\/strong>[56.8]<br>\u6211\u3005\u306fFlashAdventure\u3092\u7d39\u4ecb\u3057\u305f\u3002\u3053\u308c\u306f\u3001\u30d5\u30eb\u30b9\u30c8\u30fc\u30ea\u30fc\u306e\u30a2\u30fc\u30af\u88dc\u5b8c\u3092\u30c6\u30b9\u30c8\u3059\u308b\u305f\u3081\u306b\u8a2d\u8a08\u3055\u308c\u305f\u300134\u306eFlash\u30d9\u30fc\u30b9\u306e\u30a2\u30c9\u30d9\u30f3\u30c1\u30e3\u30fc\u30b2\u30fc\u30e0\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308b\u3002 \u307e\u305f,\u30b2\u30fc\u30e0\u30d7\u30ec\u30a4\u306e\u81ea\u52d5\u8a55\u4fa1\u88c5\u7f6e\u3067\u3042\u308bCUA-as-a-Judge\u3068,\u9577\u671f\u8a18\u61b6\u3092\u5229\u7528\u3057\u305f\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308bCOAST\u3092\u63d0\u6848\u3059\u308b\u3002 \u5b9f\u9a13\u3067\u306f\u3001\u73fe\u5728\u306eGUI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u304c\u30d5\u30eb\u30b9\u30c8\u30fc\u30ea\u30fc\u306e\u30a2\u30fc\u30af\u306b\u82e6\u3057\u3080\u306e\u306b\u5bfe\u3057\u3066\u3001COAST\u306f\u89b3\u5bdf\u3068\u632f\u308b\u821e\u3044\u306e\u30ae\u30e3\u30c3\u30d7\u3092\u57cb\u3081\u308b\u3053\u3068\u3067\u30de\u30a4\u30eb\u30b9\u30c8\u30fc\u30f3\u306e\u5b8c\u4e86\u3092\u6539\u5584\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2509.01052v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2509.01052v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Mon, 01 Sep 2025 01:33:16 GMT)<\/li>\n\n\n\n<li>\u30a2\u30c9\u30d9\u30f3\u30c1\u30e3\u30fc\u30b2\u30fc\u30e0\u3092\u5229\u7528\u3057\u305f\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3068\u300cWe also propose CUA-as-a-Judge, an automated gameplay evaluator, and COAST, an agentic framework leveraging long-term clue memory to better plan and solve sequential tasks. Experiments show current GUI agents struggle with full story arcs, while COAST improves mile- stone completion by bridging the observation- behavior gap.\u300d\u3068\u3044\u3046\u8a55\u4fa1\u30b7\u30b9\u30c6\u30e0\u306e\u63d0\u6848\u3002\u73fe\u72b6\u306eSuccess Rate\u306f\u3068\u3066\u3082\u4f4e\u3044\u304c\u4eca\u5f8c\u3069\u306e\u304f\u3089\u3044\u306e\u901f\u5ea6\u3067\u6539\u5584\u3057\u3066\u3044\u304f\u304b\u304c\u697d\u3057\u307f\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/ahnjaewoo.github.io\/flashadventure\/\">FlashAdventure<\/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":[517,647],"class_list":["post-7395","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-517","tag-647"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7395","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=7395"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7395\/revisions"}],"predecessor-version":[{"id":7396,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7395\/revisions\/7396"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7395"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7395"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7395"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}