{"id":13556,"date":"2026-10-19T17:01:20","date_gmt":"2026-10-19T09:01:20","guid":{"rendered":"https:\/\/infernews.com\/blog\/into-the-unknown-2\/"},"modified":"2026-10-19T17:09:10","modified_gmt":"2026-10-19T09:09:10","slug":"into-the-unknown-2","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/into-the-unknown-2\/","title":{"rendered":"into-the-unknown\uff1a\u63a2\u7d22\u672a\u77e5\uff1aAI \u667a\u80fd\u9ad4\u80fd\u81ea\u4e3b\u64b0\u5beb\u79d1\u5b78\u8ad6\u6587\u55ce\uff1f"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/10\/into-the-unknown-AI-1.jpg\" alt=\"A path climbs a mountain under the night sky to an open door full of stars\"\/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u8207\u5176\u8acb AI \u5beb\u6458\u8981\u3001\u6539\u6539 bug\uff0c\u300cInto the Unknown\u300d\u8981\u6c42 Agent \u5f9e\u96f6\u5b8c\u6210\u4e00\u6bb5\u5c0f\u578b\u7814\u7a76\uff1a\u95b1\u8b80\u4e00\u7bc7\u79d1\u5b78\u5bb6\u5beb\u7684\u8ad6\u6587\uff0c\u518d\u4f9d\u64da\u79d1\u5b78\u5bb6\u89aa\u81ea\u63d0\u51fa\u7684\u5ef6\u4f38\u65b9\u5411\uff0c\u8dd1\u5be6\u9a57\u3001\u6536\u96c6\u7d50\u679c\uff0c\u6700\u5f8c\u4ea4\u51fa\u4e00\u7bc7\u8aa0\u5be6\u4e14\u5b8c\u6574\u7684\u5f8c\u7e8c\u8ad6\u6587\u300215 \u9053\u984c\u76ee\u6a6b\u8de8\u4e0d\u540c\u5b78\u79d1\uff0c\u6bcf\u4e00\u9053\u90fd\u4f86\u81ea\u771f\u6b63\u505a\u7814\u7a76\u7684\u4eba\u5c0d\u81ea\u5df1\u5de5\u4f5c\u7684\u4e0b\u4e00\u6b65\u69cb\u60f3\uff0c\u800c\u4e0d\u662f\u5f9e\u516c\u958b\u8cc7\u6599\u5eab\u62fc\u6e4a\u51fa\u4f86\u7684\u4eba\u5de5\u984c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u91dd\u5c0d\u60f3\u505a\u6bd4\u8f03\u7684\u4eba\uff0c\u914d\u5957\u5df2\u7d93\u9f4a\u5099\uff1aHugging Face \u4e0a\u91cb\u51fa\u8cc7\u6599\u96c6\u8207 Agent \u5b8c\u6574\u8ecc\u8de1\u3001\u6a94\u6848\u7cfb\u7d71\u8207\u7522\u51fa\u8ad6\u6587\uff0c\u7db2\u7ad9\u8a2d\u6709\u6392\u884c\u699c\uff0c\u6b61\u8fce\u63d0\u4ea4\u65b0 Agent \u7684\u8ad6\u6587\u3002Agent \u7aef\u652f\u63f4 Claude Agent SDK\uff08opus-4.8\u3001opus-5\u3001opus-5.5\u3001fable-5\uff09\u3001OpenAI Codex \u7cfb\u5217\uff08sol-5.6\u3001astra-6\uff09\uff0c\u4ee5\u53ca\u4ee5 OpenHands \u70ba\u5e95\u5c64\u7684 glm-5.3\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\\\/6469949654873f0043b09c22\\\/92mI-u-kuSJ3RaKpEPXsn.mp4&quot;,&quot;ratio&quot;:&quot;&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;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\">\u60f3\u81ea\u5efa\u8a55\u6e2c\u6d41\u7a0b\uff0c\u53ea\u8981 <code>git clone<\/code> \u5132\u5b58\u5eab\u3001\u57f7\u884c <code>prepare_tasks.py<\/code> \u628a\u6307\u5b9a\u984c\u76ee\u7684\u7a0b\u5f0f\u78bc\u8207\u8cc7\u6599\u4e0b\u8f09\u5230 <code>tasks\/paper{1..15}\/<\/code>\uff0c\u518d\u5b89\u88dd\u5c0d\u61c9 Agent \u6846\u67b6\u5373\u53ef\u9010\u984c\u8a55\u4f30\u3002\u9019\u6a23\u505a\u7684\u597d\u8655\u662f\u53ef\u4ee5\u91cd\u73fe Agent \u7684\u57f7\u884c\u8def\u5f91\u8207\u6a94\u6848\u7cfb\u7d71\uff0c\u5f8c\u7e8c\u5be9\u8996\u5176\u8ad6\u6587\u662f\u5426\u771f\u5be6\u53cd\u6620\u5be6\u9a57\u7d50\u679c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u8207\u4e00\u822c benchmark \u4e0d\u540c\uff0c\u5b83\u8003\u6838\u7684\u4e0d\u53ea\u662f\u7b54\u5c0d\u6216\u7b54\u932f\uff0c\u800c\u662f Agent \u9762\u5c0d\u958b\u653e\u3001\u672a\u5b9a\u7fa9\u7684\u7814\u7a76\u554f\u984c\u6642\uff0c\u80fd\u5426\u7dad\u6301\u5b78\u8853\u8aa0\u4fe1\u4e26\u7522\u51fa\u7b26\u5408\u9818\u57df\u6a19\u6e96\u7684\u6210\u679c\u3002\u9019\u5c0d\u505a AI for Science\u3001Agent \u8a55\u6e2c\uff0c\u4ee5\u53ca\u60f3\u4e86\u89e3 Agent \u5728\u9577\u7a0b\u79d1\u5b78\u4efb\u52d9\u4e0a\u74f6\u9838\u7684\u5718\u968a\u7279\u5225\u6709\u53c3\u8003\u50f9\u503c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/prometheus-eval.github.io\/into-the-unknown\/viewer\/#\/\" rel=\"noopener noreferrer\"><strong>\u9805\u76ee\u4e3b\u9801<\/strong><\/a> \u00b7 <a href=\"https:\/\/github.com\/prometheus-eval\/into-the-unknown\" rel=\"noopener noreferrer\"><strong>GitHub<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u628a 15 \u500b\u9818\u57df\u79d1\u5b78\u5bb6\u89aa\u81ea\u70ba\u81ea\u5df1\u8ad6\u6587\u63d0\u51fa\u7684\u5ef6\u4f38\u65b9\u5411\u4ea4\u7d66 AI Agent\uff0c\u8981\u6c42 Agent \u771f\u7684\u628a\u7814\u7a76\u505a\u51fa\u4f86\u4e26\u5beb\u6210\u5f8c\u7e8c\u8ad6\u6587\u3002<\/p>\n","protected":false},"author":8,"featured_media":13555,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"wpai_generated_summary":"","wpai_meta_description":"","footnotes":""},"categories":[133,116,153,137,197,114,150,191,199],"tags":[],"class_list":["post-13556","post","type-post","status-publish","format-standard","hentry","category-133","category-agentic","category-openai","category-api","category-framework","category-clone","category-150","category-anthropic","category-dataset-"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/13556","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=13556"}],"version-history":[{"count":2,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/13556\/revisions"}],"predecessor-version":[{"id":13560,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/13556\/revisions\/13560"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/13555"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=13556"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=13556"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=13556"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}