{"id":14524,"date":"2026-11-04T20:03:45","date_gmt":"2026-11-04T12:03:45","guid":{"rendered":"https:\/\/infernews.com\/blog\/embodied-agent-arena\/"},"modified":"2026-11-04T21:33:58","modified_gmt":"2026-11-04T13:33:58","slug":"embodied-agent-arena","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/embodied-agent-arena\/","title":{"rendered":"Embodied Agent Arena\uff1a\u6e2c\u8a66\u5341\u6b3e VLM \u7684\u4efb\u52d9\u80fd\u529b"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/11\/Embodied-Agent-Arena-VLM.jpg\" alt=\"logo transparent\"\/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u8981\u5224\u65b7\u8996\u89ba\u8a9e\u8a00\u6a21\u578b\uff08Vision-Language Models\uff0cVLMs\uff09\u80fd\u5426\u52dd\u4efb\u6a5f\u68b0\u4eba\u901a\u7528\u64cd\u4f5c\uff0c\u4e0d\u80fd\u53ea\u770b\u5b83\u6709\u6c92\u6709\u6210\u529f\u767c\u51fa\u52d5\u4f5c\u3002Embodied Agent Arena \u662f\u4e00\u500b\u5177\u8eab\u4ee3\u7406\u8a55\u6e2c\u9805\u76ee\uff0c\u4ee5\u5171\u540c\u6e2c\u8a66\u6d41\u7a0b\u6bd4\u8f03\u5341\u6b3e\u6a21\u578b\u5728\u4e94\u985e\u80fd\u529b\u4e0a\u7684\u8868\u73fe\uff0c\u6db5\u84cb 1,000 \u500b\u6848\u4f8b\uff0c\u4e26\u628a\u5e7e\u4f55\u7406\u89e3\u3001\u7a7a\u9593\u63a8\u7406\u548c\u8996\u89ba\u5b9a\u4f4d\u7d0d\u5165\u8a55\u6e2c\u3002<\/p>\n\n\n<div\n    \tclass=\"align wp-block-vpb-video\"    id='vpbpVideoPlayer-1'\n    data-attributes='{&quot;source&quot;:&quot;https:\\\/\\\/cdn-uploads.huggingface.co\\\/production\\\/uploads\\\/657a776153e2fa36fed33259\\\/s7kSluiNqt9a6ZAxBGZEB.mp4&quot;,&quot;repeat&quot;:true,&quot;autoplay&quot;:true,&quot;muted&quot;:true,&quot;align&quot;:&quot;&quot;,&quot;poster&quot;:&quot;&quot;,&quot;controls&quot;:{&quot;play-large&quot;:true,&quot;restart&quot;:false,&quot;rewind&quot;:true,&quot;play&quot;:true,&quot;fast-forward&quot;:true,&quot;progress&quot;:true,&quot;current-time&quot;:true,&quot;duration&quot;:false,&quot;mute&quot;:true,&quot;volume&quot;:true,&quot;pip&quot;:false,&quot;airplay&quot;:false,&quot;captions&quot;:false,&quot;settings&quot;:true,&quot;download&quot;:false,&quot;fullscreen&quot;:true},&quot;captions&quot;:[],&quot;ratio&quot;:&quot;16:9&quot;,&quot;accentColor&quot;:&quot;&quot;,&quot;lazyLoad&quot;:false,&quot;width&quot;:&quot;100%&quot;,&quot;radius&quot;:&quot;0px&quot;,&quot;resetOnEnd&quot;:false,&quot;autoHideControl&quot;:true,&quot;isSetup&quot;:false}'\n><\/div>\n\n\n<p class=\"wp-block-paragraph\">\u9805\u76ee\u628a\u4efb\u52d9\u7406\u89e3\u3001\u63a8\u7406\u548c\u52d5\u4f5c\u9078\u64c7\u4ea4\u7531\u6a21\u578b\u8655\u7406\uff0c\u518d\u4ee5\u540c\u4e00\u5957\u7cbe\u7c21\u8a55\u6e2c\u6846\u67b6\u6e2c\u8a66\u4e0d\u540c\u6a21\u578b\u3002\u6e2c\u8a66\u8cc7\u6599\u6574\u5408 32 \u500b\u65e2\u6709\u4f86\u6e90\uff0c\u53e6\u52a0\u5165 168 \u500b\u6848\u4f8b\u7684 GeoProbe \u5e7e\u4f55\u57fa\u6e96\uff1b\u76f8\u6bd4\u53ea\u770b\u6a5f\u68b0\u4eba\u4e92\u52d5\u4efb\u52d9\uff0c\u9019\u7a2e\u5b89\u6392\u80fd\u540c\u6642\u6aa2\u8996\u6a21\u578b\u7406\u89e3\u7a7a\u9593\u8cc7\u8a0a\u7684\u80fd\u529b\uff0c\u4ee5\u53ca\u80fd\u529b\u80fd\u5426\u8f49\u5316\u70ba\u5be6\u969b\u4efb\u52d9\u6210\u679c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u7d50\u679c\u53cd\u6620\uff0c\u55ae\u4e00\u6307\u6a19\u5bb9\u6613\u63a9\u84cb\u4efb\u52d9\u662f\u5426\u771f\u6b63\u5b8c\u6210\u3002<mark>Gemini 4 Argon \u7684 3D \u8def\u5f91\u8aa4\u5dee\u6700\u4f4e<\/mark>\uff0c\u70ba 0.310 \u7c73\uff0c\u4f46 56 \u689d\u8def\u5f91\u4e2d\u53ea\u6709 24 \u689d\u7b26\u5408\u5168\u90e8\u9650\u5236\uff1bManipulation \u6210\u529f\u7387\u6700\u9ad8\u7684 Opus 5.5 \u4ea6\u53ea\u6709 47.8%\u3002CALVIN \u6e2c\u8a66\u4e2d\uff0c100 \u500b\u5e8f\u5217\u6709 60 \u500b\u5b8c\u6210\u7b2c\u4e00\u500b\u76ee\u6a19\uff0c\u5b8c\u6210\u5168\u90e8\u4e94\u500b\u76ee\u6a19\u7684\u53ea\u6709 9 \u500b\uff1b\u5728\u4e94\u9805 ManiSkill \u8a3a\u65b7\u4efb\u52d9\u4e2d\uff0cOpus 5.5 \u80fd\u5b8c\u6210\u62fe\u53d6\u3001\u653e\u7f6e\u548c\u5806\u758a\uff0c\u537b\u672a\u80fd\u5b8c\u6210\u63d2\u5165\u63d2\u92b7\u6216\u5145\u96fb\u5668\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u540c\u4e00\u6279 157 \u9805 Planning \u4efb\u52d9\u4e2d\uff0c\u81f3\u5c11\u6709\u4e00\u6b3e\u6a21\u578b\u5b8c\u6210 142 \u9805\uff1b\u4ecd\u6709 15 \u9805\u5341\u6b3e\u6a21\u578b\u5168\u90e8\u5931\u6557\u3002<\/li>\n\n\n\n<li>Astra \u7684 31 \u9805\u5931\u6557\u4efb\u52d9\u8017\u7528 55.5% token\uff1b\u5931\u6557\u4efb\u52d9\u5e73\u5747\u8017\u7528\u7684 token \u662f\u6210\u529f\u4efb\u52d9\u7684 5.1 \u500d\u3002<\/li>\n\n\n\n<li>CALVIN \u6709 65 \u500b\u5e8f\u5217\u66fe\u9047\u5230\u57f7\u884c\u932f\u8aa4\uff1b\u5176\u4e2d 62 \u500b\u5f8c\u4f86\u80fd\u7121\u932f\u57f7\u884c\u7a0b\u5f0f\u78bc\uff0c\u4f46\u53ea\u6709 3 \u500b\u6700\u7d42\u5b8c\u6210\u5e8f\u5217\u3002<\/li>\n\n\n\n<li>Case Atlas \u6536\u9304 181 \u500b\u6db5\u84cb\u4e94\u985e\u80fd\u529b\u7684\u6848\u4f8b\uff0c\u63d0\u4f9b\u5341\u6b3e\u6a21\u578b\u7684\u7d00\u9304\uff1b\u7f3a\u5c11\u5f71\u7247\u7684\u9805\u76ee\u6703\u4f7f\u7528\u5171\u7528\u4efb\u52d9\u5834\u666f\uff0cAPI \u4e2d\u65b7\u5247\u6a19\u8a18\u70ba\u5931\u6557\u5617\u8a66\u3002<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u9019\u4e9b\u7d50\u679c\u9069\u5408\u7528\u4f86\u6bd4\u8f03\u6a21\u578b\u5728\u54ea\u4e9b\u74b0\u7bc0\u5931\u624b\uff0c\u4ea6\u63d0\u9192\u7814\u7a76\u5718\u968a\u4e0d\u8981\u628a\u8def\u5f91\u7cbe\u5ea6\u3001\u7a0b\u5f0f\u78bc\u57f7\u884c\u6210\u529f\u6216\u55ae\u4e00\u6b65\u9a5f\u64cd\u4f5c\uff0c\u76f4\u63a5\u7576\u6210\u5b8c\u6574\u4efb\u52d9\u80fd\u529b\u3002\u9805\u76ee\u63d0\u4f9b\u7dda\u4e0a\u7d50\u679c\u3001\u6848\u4f8b\u5f71\u7247\u3001\u8cc7\u6599\u96c6\u53ca\u7a0b\u5f0f\u78bc\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/embodied-agent-arena.github.io\/embodied-agent-arena\/\" rel=\"noopener\" target=\"_blank\"><strong>\u9805\u76ee\u4e3b\u9801<\/strong><\/a> \u00b7 <a href=\"https:\/\/github.com\/embodied-agent-arena\/embodied-agent-arena\" rel=\"noopener\" target=\"_blank\"><strong>GitHub<\/strong><\/a> \u00b7 <a href=\"https:\/\/huggingface.co\/datasets\/uuu-Quant\/Embodied-Agent-Arena\" rel=\"noopener\" target=\"_blank\"><strong>\u6578\u64da\u96c6<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u5341\u6b3e\u524d\u6cbf\u8996\u89ba\u8a9e\u8a00\u6a21\u578b\u63a5\u53d7 1,000 \u500b\u5177\u8eab\u4efb\u52d9\u6e2c\u8a66\uff0c\u7d50\u679c\u986f\u793a\uff0c\u80fd\u751f\u6210\u53ef\u57f7\u884c\u52d5\u4f5c\uff0c\u4e0d\u4ee3\u8868\u80fd\u5b8c\u6210\u591a\u6b65\u64cd\u4f5c\u6216\u7cbe\u7d30\u63a5\u89f8\u4efb\u52d9\u3002<\/p>\n","protected":false},"author":8,"featured_media":14523,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"wpai_generated_summary":"","wpai_meta_description":"","footnotes":""},"categories":[133,164,165,116,162,186,185,147,140,137,204,184,197,163,191,199],"tags":[],"class_list":["post-14524","post","type-post","status-publish","format-standard","hentry","category-133","category-164","category-165","category-agentic","category-ai-productions","category-186","category-qwen","category-deepseek","category-gemini","category-api","category-visionlanguageaction","category-robotic","category-framework","category-163","category-anthropic","category-dataset-"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/14524","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=14524"}],"version-history":[{"count":2,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/14524\/revisions"}],"predecessor-version":[{"id":14530,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/14524\/revisions\/14530"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/14523"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=14524"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=14524"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=14524"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}