{"id":7627,"date":"2025-10-28T05:22:00","date_gmt":"2025-10-27T20:22:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7627"},"modified":"2025-10-18T15:26:13","modified_gmt":"2025-10-18T06:26:13","slug":"lm-fight-arena-benchmarking-large-multimodal-models-via-game-competition","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7627","title":{"rendered":"LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>LM Fight Arena: Benchmarking Large Multimodal Models via Game Competition\u00a0<\/strong>[104.8]<br>\u672c\u7a3f\u3067\u306f,Mortal Kombat II\u306b\u304a\u3051\u308b\u5927\u898f\u6a21\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30e2\u30c7\u30eb\u3092\u8a55\u4fa1\u3059\u308b\u65b0\u3057\u3044\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308bLM Fight Arena\u3092\u7d39\u4ecb\u3059\u308b\u3002 \u9759\u7684\u8a55\u4fa1\u3068\u306f\u7570\u306a\u308a\u3001LM Fight Arena\u306f\u5b8c\u5168\u306b\u81ea\u52d5\u5316\u3055\u308c\u3001\u518d\u73fe\u53ef\u80fd\u3067\u3001LMM\u306e\u6226\u7565\u7684\u63a8\u8ad6\u80fd\u529b\u306e\u5ba2\u89b3\u7684\u8a55\u4fa1\u3092\u63d0\u4f9b\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2510.08928v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2510.08928v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 10 Oct 2025 02:19:21 GMT)<\/li>\n\n\n\n<li>\u300cUnlike static evaluations, LM Fight Arena provides a fully automated, reproducible, and objective assessment of an LMM\u2019s strategic reasoning capabilities in a dynamic setting. This work introduces a challenging and engaging benchmark that bridges the gap between AI evaluation and interactive entertainment.\u300d\u3068\u306e\u3053\u3068\u3060\u304c\u3001\u306a\u305c\u306bMortal Kombat&#8230;<\/li>\n\n\n\n<li>Claude 3.5 Sonnet\u304c\u3068\u3066\u3082\u5f37\u3044\u3089\u3057\u3044\u3002<\/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],"class_list":["post-7627","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7627","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=7627"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7627\/revisions"}],"predecessor-version":[{"id":7628,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7627\/revisions\/7628"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7627"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7627"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7627"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}