{"id":7267,"date":"2025-08-14T05:49:00","date_gmt":"2025-08-13T20:49:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7267"},"modified":"2025-08-11T14:52:36","modified_gmt":"2025-08-11T05:52:36","slug":"coact-1-computer-using-agents-with-coding-as-actions","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7267","title":{"rendered":"CoAct-1: Computer-using Agents with Coding as Actions"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>CoAct-1: Computer-using Agents with Coding as Actions\u00a0<\/strong>[95.0]<br>CoAct-1\u306fGUI\u30d9\u30fc\u30b9\u306e\u5236\u5fa1\u3068\u76f4\u63a5\u30d7\u30ed\u30b0\u30e9\u30e0\u5b9f\u884c\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u65b0\u3057\u3044\u30de\u30eb\u30c1\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30b7\u30b9\u30c6\u30e0\u3067\u3042\u308b\u3002 \u6211\u3005\u306f\u3001CoAct-1\u304c60.76%\u306e\u6700\u5148\u7aef\u306e\u6210\u529f\u7387\u3092\u9054\u6210\u3057\u305fOSWorld\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3001\u6211\u3005\u306e\u30b7\u30b9\u30c6\u30e0\u3092\u8a55\u4fa1\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2508.03923v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2508.03923v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 05 Aug 2025 21:33:36 GMT)<\/li>\n\n\n\n<li>\u300cCoAct-1 features an Orchestrator that dynamically delegates subtasks to either a conventional GUI Operator or a specialized Programmer agent, which can write and execute Python or Bash scripts. This hybrid approach allows the agent to bypass inefficient GUI action sequences for tasks like file management and data processing, while still leveraging visual interaction when necessary.\u300d\u3068\u30b3\u30fc\u30c9\u751f\u6210\u3092\u3046\u307e\u304f\u4f7f\u3046GUI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306e\u63d0\u6848\u3002OS World\u3067SoTA\u3092\u4e3b\u5f35\u3002<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/linxins.net\/coact\/\">CoAct-1<\/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-7267","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\/7267","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=7267"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7267\/revisions"}],"predecessor-version":[{"id":7268,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7267\/revisions\/7268"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7267"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7267"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7267"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}