{"id":7301,"date":"2025-08-18T09:03:00","date_gmt":"2025-08-18T00:03:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7301"},"modified":"2025-08-17T21:05:37","modified_gmt":"2025-08-17T12:05:37","slug":"os-agents-a-survey-on-mllm-based-agents-for-general-computing-devices-use","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7301","title":{"rendered":"OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use\u00a0<\/strong>[101.6]<br>\u30a2\u30a4\u30a2\u30f3\u30de\u30f3\u306e\u67b6\u7a7a\u306eJ.A.R.V.I.S\u307b\u3069\u6709\u80fd\u3067\u591a\u7528\u9014\u306aAI\u30a2\u30b7\u30b9\u30bf\u30f3\u30c8\u3092\u4f5c\u308b\u5922\u306f\u3001\u9577\u3044\u9593\u60f3\u50cf\u529b\u306b\u6075\u307e\u308c\u3066\u304d\u305f\u3002 \u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb(multi-modal)\u306a\u5927\u304d\u306a\u8a00\u8a9e\u30e2\u30c7\u30eb((M)LLMs)\u306e\u9032\u5316\u306b\u3088\u308a\u3001\u3053\u306e\u5922\u306f\u73fe\u5b9f\u306b\u8fd1\u3065\u3044\u3066\u3044\u308b\u3002 \u672c\u8abf\u67fb\u306f,OS\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u7814\u7a76\u306e\u73fe\u72b6\u3092\u6574\u7406\u3057,\u5b66\u8853\u8abf\u67fb\u3068\u7523\u696d\u958b\u767a\u306e\u4e21\u65b9\u306e\u6307\u91dd\u3092\u63d0\u4f9b\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2508.04482v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2508.04482v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 06 Aug 2025 14:33:45 GMT)<\/li>\n\n\n\n<li>\u300cThe dream to create AI assistants as capable and versatile as the fictional J.A.R.V.I.S from Iron Man has long captivated imaginations. With the evolution of (multimodal) large language models ((M)LLMs), this dream is closer to reality, as (M)LLM-based Agents using computing devices (e g , computers and mobile phones) by operating within the environments and interfaces (e g , Graphical User Interface (GUI)) provided by operating systems (OS) to automate tasks have significantly advanced.\u300d\u304b\u3089\u59cb\u307e\u308b\u30b5\u30fc\u30d9\u30a4\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/os-agent-survey.github.io\/\">OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (ACL 2025)<\/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":[181,387],"class_list":["post-7301","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-gui-agent","tag-survey"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7301","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=7301"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7301\/revisions"}],"predecessor-version":[{"id":7302,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7301\/revisions\/7302"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7301"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7301"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7301"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}