{"id":34545,"date":"2024-12-08T17:56:25","date_gmt":"2024-12-08T09:56:25","guid":{"rendered":"https:\/\/17aitech.com\/?p=34545"},"modified":"2024-12-08T17:56:25","modified_gmt":"2024-12-08T09:56:25","slug":"%e7%99%bb%e9%a1%b6%e5%bc%80%e6%ba%90ai%e8%bd%af%e4%bb%b6%e5%b7%a5%e7%a8%8b%e5%b8%88%e6%a6%9c%e9%a6%96%ef%bc%8cuiuc%e6%97%a0agent%e6%96%b9%e6%a1%88%e8%bd%bb%e6%9d%be%e8%a7%a3%e5%86%b3swe-bench%e7%9c%9f","status":"publish","type":"post","link":"https:\/\/17aitech.com\/?p=34545","title":{"rendered":"\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u699c\u9996\uff0cUIUC\u65e0Agent\u65b9\u6848\u8f7b\u677e\u89e3\u51b3SWE-bench\u771f\u5b9e\u7f16\u7a0b\u95ee\u9898"},"content":{"rendered":"<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:<a href=\"https:\/\/www.jiqizhixin.com\/articles\/2024-07-15-12\" target=\"_blank\">\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u699c\u9996\uff0cUIUC\u65e0Agent\u65b9\u6848\u8f7b\u677e\u89e3\u51b3SWE-bench\u771f\u5b9e\u7f16\u7a0b\u95ee\u9898<\/a><\/p>\n<section><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0109fcad6d51c97f8f50d37f1fad6e2b.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0109fcad6d51c97f8f50d37f1fad6e2b.png\"><\/a><\/section>\n<blockquote data-author-name=\"\" data-content-utf8-length=\"166\" data-source-title=\"\" data-type=\"2\" data-url=\"\">\n<section>\n<section>AIxiv\u4e13\u680f\u662f<mark data-type=\"institutions\" data-id=\"9e96434f-5827-41e3-9b3c-36d39bc0d446\">\u673a\u5668\u4e4b\u5fc3<\/mark>\u53d1\u5e03\u5b66\u672f\u3001\u6280\u672f\u5185\u5bb9\u7684\u680f\u76ee\u3002\u8fc7\u53bb\u6570\u5e74\uff0c<mark data-type=\"institutions\" data-id=\"9e96434f-5827-41e3-9b3c-36d39bc0d446\">\u673a\u5668\u4e4b\u5fc3<\/mark>AIxiv\u4e13\u680f\u63a5\u6536\u62a5\u9053\u4e862000\u591a\u7bc7\u5185\u5bb9\uff0c\u8986\u76d6\u5168\u7403\u5404\u5927\u9ad8\u6821\u4e0e\u4f01\u4e1a\u7684\u9876\u7ea7\u5b9e\u9a8c\u5ba4\uff0c\u6709\u6548\u4fc3\u8fdb\u4e86\u5b66\u672f\u4ea4\u6d41\u4e0e\u4f20\u64ad\u3002\u5982\u679c\u60a8\u6709\u4f18\u79c0\u7684\u5de5\u4f5c\u60f3\u8981\u5206\u4eab\uff0c\u6b22\u8fce\u6295\u7a3f\u6216\u8005\u8054\u7cfb\u62a5\u9053\u3002\u6295\u7a3f\u90ae\u7bb1\uff1aliyazhou@jiqizhixin.com\uff1bzhaoyunfeng@jiqizhixin.com<\/section>\n<\/section>\n<\/blockquote>\n<p><strong>\u8fd9\u7bc7\u8bba\u6587\u7684\u4f5c\u8005\u5747\u6765\u81ea\u4f0a\u5229\u8bfa\u4f0a\u5927\u5b66\u9999\u69df\u5206\u6821\uff08UIUC\uff09\u5f20\u4ee4\u660e\u8001\u5e08\u56e2\u961f\uff0c\u5305\u62ec\uff1aSteven Xia\uff0c\u56db\u5e74\u7ea7\u535a\u58eb\u751f\uff0c\u7814\u7a76\u65b9\u5411\u662f\u57fa\u4e8e AI \u5927\u6a21\u578b\u7684\u81ea\u52a8\u4ee3\u7801\u4fee\u590d\uff1b\u9093\u8335\u7433\uff0c\u56db\u5e74\u7ea7\u535a\u58eb\u751f\uff0c\u7814\u7a76\u65b9\u5411\u662f\u57fa\u4e8e AI \u5927\u6a21\u578b\u7684\u4ee3\u7801\u751f\u6210\uff1bSoren Dunn\uff0c\u79d1\u7814\u5b9e\u4e60\u751f\uff0c\u76ee\u524d\u4e3a UIUC \u5927\u4e09\u5b66\u751f\u3002\u5f20\u4ee4\u660e\u8001\u5e08\u73b0\u4efb UIUC \u8ba1\u7b97\u673a\u7cfb\u526f\u6559\u6388\uff0c\u4e3b\u8981\u4ece\u4e8b\u8f6f\u4ef6\u5de5\u7a0b\u3001<mark data-type=\"tech_methods\" data-id=\"1a0e9c5e-6502-4cd7-8683-6b5ca6c48be2\">\u673a\u5668\u5b66\u4e60<\/mark>\u3001\u4ee3\u7801\u5927\u6a21\u578b\u7684\u76f8\u5173\u7814\u7a76\u3002<\/strong><\/p>\n<p><strong>\u66f4\u591a\u8be6\u7ec6\u4fe1\u606f\u8bf7\u89c1\u5f20\u8001\u5e08\u7684\u4e2a\u4eba\u4e3b\u9875\uff1ahttps:\/\/lingming.cs.illinois.edu\/<\/strong><\/p>\n<p>\u81ea\u4ece Devin\uff08\u9996\u4e2a\u5168\u81ea\u52a8 AI \u8f6f\u4ef6\u5de5\u7a0b\u5e08\uff09\u63d0\u51fa\u4ee5\u6765\uff0c\u9488\u5bf9\u8f6f\u4ef6\u5de5\u7a0b\u7684 AI Agent \u7684\u8bbe\u8ba1\u6210\u4e3a\u7814\u7a76\u7684\u7126\u70b9\uff0c\u8d8a\u6765\u8d8a\u591a\u57fa\u4e8e Agent \u7684 AI \u81ea\u52a8\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u88ab\u63d0\u51fa\uff0c\u5e76\u5728 SWE-bench \u6570\u636e\u96c6\u4e0a\u53d6\u5f97\u4e86\u4e0d\u4fd7\u7684\u8868\u73b0\u3001\u81ea\u52a8\u4fee\u590d\u4e86\u8bb8\u591a\u771f\u5b9e\u7684 GitHub issue\u3002<\/p>\n<p>\u7136\u800c\uff0c\u590d\u6742\u7684 Agent \u7cfb\u7edf\u4f1a\u5e26\u6765\u989d\u5916\u7684\u5f00\u9500\u548c\u4e0d\u786e\u5b9a\u6027\uff0c\u6211\u4eec\u771f\u7684\u9700\u8981\u4f7f\u7528\u5982\u6b64\u590d\u6742\u7684 Agent \u6765\u89e3\u51b3 GitHub issue \u5417\uff1f\u4e0d\u4f9d\u8d56 Agent \u7684\u89e3\u51b3\u65b9\u6848\u80fd\u63a5\u8fd1\u5b83\u4eec\u7684\u6027\u80fd\u5417\uff1f<\/p>\n<p>\u4ece\u8fd9\u4e24\u4e2a\u95ee\u9898\u51fa\u53d1\uff0c\u4f0a\u5229\u8bfa\u4f0a\u5927\u5b66\u9999\u69df\u5206\u6821\uff08UIUC\uff09\u5f20\u4ee4\u660e\u8001\u5e08\u56e2\u961f\u63d0\u51fa\u4e86 OpenAutoCoder-Agentless\uff0c\u4e00\u4e2a\u7b80\u5355\u9ad8\u6548\u5e76\u4e14\u5b8c\u5168\u5f00\u6e90\u7684\u65e0 Agent \u65b9\u6848\uff0c\u4ec5\u9700 $0.34 \u5c31\u80fd\u89e3\u51b3\u4e00\u4e2a\u771f\u5b9e\u7684 GitHub issue\u3002Agentless \u5728\u77ed\u77ed\u51e0\u5929\u5185\u5728 GitHub \u4e0a\u5df2\u7ecf\u5438\u5f15\u4e86\u8d85\u8fc7 300 GitHub Star\uff0c\u5e76\u767b\u4e0a\u4e86 DAIR.AI \u6bcf\u5468\u6700\u70ed ML \u8bba\u6587\u699c\u5355\u524d\u4e09\u3002<\/p>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-3e0e143d65389ea3ee1f59e38df3e6c6.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-3e0e143d65389ea3ee1f59e38df3e6c6.png\"><\/a><\/p>\n<ul>\n<li>\n<p>\u8bba\u6587\uff1aAGENTLESS : Demystifying LLM-based Software Engineering Agents<\/p>\n<\/li>\n<li>\n<p>\u8bba\u6587\u5730\u5740\uff1ahttps:\/\/huggingface.co\/papers\/2407.01489<\/p>\n<\/li>\n<li>\n<p>\u5f00\u6e90\u4ee3\u7801\uff1ahttps:\/\/github.com\/OpenAutoCoder\/Agentless<\/p>\n<\/li>\n<\/ul>\n<p>AWS \u7814\u7a76\u79d1\u5b66\u5bb6 Leo Boytsov \u8868\u793a\uff1a\u201cAgentless \u6846\u67b6\u8868\u73b0\u4f18\u5f02\uff0c\u8d85\u8fc7\u6240\u6709\u5f00\u6e90 Agent \u89e3\u51b3\u65b9\u6848\uff0c\u51e0\u4e4e\u8fbe\u5230 SWE Bench Lite \u6700\u9ad8\u6c34\u5e73\uff0827%\uff09\u3002\u800c\u4e14\uff0c\u5b83\u4ee5\u663e\u8457\u66f4\u4f4e\u7684\u6210\u672c\u51fb\u8d25\u4e86\u6240\u6709\u5f00\u6e90\u65b9\u6848\u3002\u8be5\u6846\u67b6\u91c7\u7528\u5206\u5c42<mark data-type=\"concepts\" data-id=\"bf740558-f0f7-41a8-87a0-e695a97563b3\">\u67e5\u8be2<\/mark>\u65b9\u6cd5\uff08\u901a\u8fc7\u5411 LLM \u63d0\u95ee\u6765\u67e5\u627e\u6587\u4ef6\u3001\u7c7b\u3001\u51fd\u6570\u7b49\uff09\u4ee5\u786e\u5b9a\u8865\u4e01\u4f4d\u7f6e\u3002\u867d\u7136\u5229\u7528 LLM\uff0c\u4f46\u4e0d\u5141\u8bb8 LLM \u505a\u51fa<mark data-type=\"tech_tasks\" data-id=\"3f5eac69-dad3-43e7-9022-40dcf97a1892\">\u89c4\u5212<\/mark>\u51b3\u7b56\u3002\u201d<\/p>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-d911a9e4e5c8948933c665fd3ed5c6a9.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-d911a9e4e5c8948933c665fd3ed5c6a9.png\"><\/a><\/p>\n<p>Agentless \u662f\u4e00\u79cd\u81ea\u52a8\u89e3\u51b3\u8f6f\u4ef6\u5f00\u53d1\u95ee\u9898\u7684\u65b9\u6cd5\uff0c\u5b83\u4f7f\u7528\u7b80\u5355\u7684\u4e24\u9636\u6bb5\u65b9\u6cd5\u8fdb\u884c\u5b9a\u4f4d\u548c\u4fee\u590d\uff0c\u4ee5\u4fee\u590d\u4ee3\u7801\u5e93\u4e2d\u7684 bug\u3002\u5728\u5b9a\u4f4d\u9636\u6bb5\uff0cAgentless \u4ee5\u5206\u5c42\u65b9\u5f0f\u6765\u9010\u6b65\u7f29\u5c0f\u5230\u53ef\u7591\u7684\u6587\u4ef6\u3001\u7c7b \/ \u51fd\u6570\u548c\u5177\u4f53\u7684\u7f16\u8f91\u4f4d\u7f6e\u3002\u5bf9\u4e8e\u4fee\u590d\uff0c\u5b83\u4f7f\u7528\u7b80\u5355\u7684 diff \u683c\u5f0f\uff08\u53c2\u8003\u81ea\u5f00\u6e90\u5de5\u5177 Aider\uff09\u6765\u751f\u6210\u591a\u4e2a\u5019\u9009\u8865\u4e01\uff0c\u5e76\u5bf9\u5176\u8fdb\u884c\u8fc7\u6ee4\u548c\u6392\u5e8f\u3002<\/p>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-d977af6a52b03835668d4ad3189ec4db.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-d977af6a52b03835668d4ad3189ec4db.png\"><\/a><\/p>\n<p>\u7814\u7a76\u8005\u5c06 Agentless \u4e0e\u73b0\u6709\u7684 AI Software Agent \u8fdb\u884c\u4e86\u6bd4\u8f83\uff0c\u5176\u4e2d\u5305\u62ec\u6700\u5148\u8fdb\u7684\u5f00\u6e90\u548c\u5546\u4e1a \/ \u95ed\u6e90\u9879\u76ee\u3002\u4ee4\u4eba\u60ca\u8bb6\u7684\u662f\uff0cAgentless \u53ef\u4ee5\u4ee5\u66f4\u4f4e\u7684\u6210\u672c\u8d85\u8d8a\u6240\u6709\u73b0\u6709\u7684\u5f00\u6e90 Software Agent\uff01Agentless \u89e3\u51b3\u4e86 27.33% \u7684\u95ee\u9898\uff0c\u662f\u5f00\u6e90\u65b9\u6848\u4e2d\u6700\u9ad8\u7684\uff0c\u5e76\u4e14\u89e3\u51b3\u6bcf\u4e2a\u95ee\u9898\u5e73\u5747\u4ec5\u9700 $0.29\uff0c\u5728\u6240\u6709\u95ee\u9898\u4e0a\uff08\u5305\u62ec\u80fd\u89e3\u51b3\u548c\u672a\u89e3\u51b3\u7684\uff09\u5e73\u5747\u53ea\u9700\u8981\u7ea6 $0.34\u3002<\/p>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-11b8faf232be837aaae65667d5778ed8.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-11b8faf232be837aaae65667d5778ed8.png\"><\/a><\/p>\n<p>\u4e0d\u4ec5\u5982\u6b64\uff0cAgentless \u8fd8\u6709\u6539\u8fdb\u7684\u6f5c\u529b\u3002\u5728\u8003\u8651\u6240\u6709\u751f\u6210\u7684\u8865\u4e01\u65f6\uff0cAgentless \u53ef\u4ee5\u89e3\u51b3 41% \u7684\u95ee\u9898\uff0c\u8fd9\u4e2a\u4e0a\u9650\u8868\u660e\u8865\u4e01\u6392\u5e8f\u548c\u9009\u62e9\u9636\u6bb5\u6709\u663e\u8457\u7684\u6539\u8fdb\u7a7a\u95f4\u3002\u6b64\u5916\uff0cAgentless \u80fd\u591f\u89e3\u51b3\u4e00\u4e9b\u5373\u4f7f\u662f\u6700\u597d\u7684\u5546\u4e1a\u5de5\u5177\uff08Alibaba Lingma Agent\uff09\u4e5f\u65e0\u6cd5\u89e3\u51b3\u7684\u72ec\u7279\u95ee\u9898\uff0c\u8fd9\u8868\u660e\u5b83\u53ef\u4ee5\u4f5c\u4e3a\u73b0\u6709\u5de5\u5177\u7684\u8865\u5145\u3002<\/p>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-fe003e6852e6d177a97392b88ac8d2d7.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-fe003e6852e6d177a97392b88ac8d2d7.png\"><\/a><\/p>\n<p><strong>\u5bf9 SWE-bench Lite \u6570\u636e\u96c6\u7684\u5206\u6790<\/strong><\/p>\n<p>\u7814\u7a76\u8005\u8fd8\u5bf9 SWE-bench Lite \u6570\u636e\u96c6\u8fdb\u884c\u4e86\u4eba\u5de5\u68c0\u67e5\u548c\u8be6\u7ec6\u5206\u6790\u3002<\/p>\n<p>\u7814\u7a76\u53d1\u73b0\uff0cSWE-bench Lite \u6570\u636e\u96c6\u4e2d\uff0c\u6709 4.3% \u7684\u95ee\u9898\u5728\u95ee\u9898\u63cf\u8ff0\u4e2d\u76f4\u63a5\u7ed9\u51fa\u4e86\u5b8c\u6574\u7684\u7b54\u6848\uff0c\u4e5f\u5c31\u662f\u6b63\u786e\u7684\u4fee\u590d\u8865\u4e01\u3002\u800c\u53e6\u5916 10% \u7684\u95ee\u9898\u63cf\u8ff0\u4e86\u6b63\u786e\u89e3\u51b3\u65b9\u6848\u7684\u786e\u5207\u6b65\u9aa4\u3002\u8fd9\u8868\u660e\uff0cSWE-bench Lite \u4e2d\u7684\u67d0\u4e9b\u95ee\u9898\u53ef\u80fd\u66f4\u5bb9\u6613\u89e3\u51b3\u3002<\/p>\n<p>\u6b64\u5916\uff0c\u7814\u7a76\u56e2\u961f\u89c2\u5bdf\u5230\u6709 4.3% \u7684\u95ee\u9898\u5728\u95ee\u9898\u63cf\u8ff0\u4e2d\u5305\u542b\u4e86\u7528\u6237\u63d0\u8bae\u7684\u89e3\u51b3\u65b9\u6848\u6216\u8005\u6b65\u9aa4\uff0c\u4f46\u8fd9\u4e9b\u65b9\u6848\u4e0e\u5f00\u53d1\u4eba\u5458\u7684\u771f\u5b9e\u8865\u4e01\u5e76\u4e0d\u4e00\u81f4\u3002\u8fd9\u8fdb\u4e00\u6b65\u63ed\u793a\u4e86\u8be5<mark data-type=\"concepts\" data-id=\"308c3a45-0fee-4ec6-858e-85b15f440fc0\">\u57fa\u51c6<\/mark>\u6d4b\u8bd5\u7684\u6f5c\u5728\u95ee\u9898\uff0c\u56e0\u4e3a\u8fd9\u4e9b\u8bef\u5bfc\u6027\u89e3\u51b3\u65b9\u6848\u53ef\u80fd\u5bfc\u81f4 AI \u5de5\u5177\u4ec5\u901a\u8fc7\u9075\u5faa\u95ee\u9898\u63cf\u8ff0\u6765\u751f\u6210\u4e0d\u6b63\u786e\u7684\u89e3\u51b3\u65b9\u6848\u3002<\/p>\n<p>\u5728\u95ee\u9898\u63cf\u8ff0\u8d28\u91cf\u65b9\u9762\uff0c\u7814\u7a76\u8005\u89c2\u5bdf\u5230\uff0c\u867d\u7136 SWE-bench Lite \u4e2d\u5927\u90e8\u5206\u7684\u4efb\u52a1\u90fd\u5305\u542b\u4e86\u8db3\u591f\u7684\u4fe1\u606f\uff0c\u5e76\u4e14\u8bb8\u591a\u4efb\u52a1\u8fd8\u63d0\u4f9b\u4e86\u5931\u8d25\u793a\u4f8b\u6765\u590d\u73b0\u9519\u8bef\uff0c\u4f46\u662f\u4ecd\u6709 9.3% \u7684\u95ee\u9898\u6ca1\u6709\u5305\u542b\u8db3\u591f\u7684\u4fe1\u606f\u3002\u4f8b\u5982\u9700\u8981\u5b9e\u73b0\u4e00\u4e2a\u65b0\u7684\u51fd\u6570\u6216\u8005\u6dfb\u52a0\u4e00\u4e2a\u9519\u8bef\u4fe1\u606f\uff0c\u4f46\u662f\u7279\u5b9a\u7684\u51fd\u6570\u540d\u6216\u8005\u7279\u5b9a\u7684\u9519\u8bef\u4fe1\u606f\u5b57\u7b26\u4e32\u5e76\u6ca1\u6709\u5728\u95ee\u9898\u63cf\u8ff0\u4e2d\u7ed9\u51fa\u3002\u8fd9\u610f\u5473\u7740\u5373\u4f7f\u6b63\u786e\u5b9e\u73b0\u4e86\u5e95\u5c42\u529f\u80fd\uff0c\u5982\u679c\u51fd\u6570\u540d\u6216\u9519\u8bef\u4fe1\u606f\u5b57\u7b26\u4e32\u4e0d\u5b8c\u5168\u5339\u914d\uff0c\u6d4b\u8bd5\u4e5f\u4f1a\u5931\u8d25\u3002<\/p>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0e5c73216ce7183e20f9c9b4b42352af.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0e5c73216ce7183e20f9c9b4b42352af.png\"><\/a><\/p>\n<p>\u666e\u6797\u65af\u987f\u5927\u5b66\u7684\u7814\u7a76\u4eba\u5458\uff0c\u540c\u65f6\u4e5f\u662f SWE-Bench \u7684\u4f5c\u8005\u4e4b\u4e00\uff0cOfir Press \u786e\u8ba4\u4e86\u4ed6\u4eec\u7684\u53d1\u73b0\uff1a\u201cAgentless \u5bf9 SWE-bench Lite \u8fdb\u884c\u4e86\u4e0d\u9519\u7684\u624b\u52a8\u5206\u6790\u3002\u4ed6\u4eec\u8ba4\u4e3a Lite \u4e0a\u7684\u7406\u8bba\u6700\u9ad8\u5f97\u5206\u53ef\u80fd\u662f 90.7%\u3002\u6211\u89c9\u5f97\u5b9e\u9645\u7684\u4e0a\u9650\u53ef\u80fd\u4f1a\u66f4\u4f4e\uff08\u5927\u7ea6 80%\uff09\u3002\u4e00\u4e9b\u95ee\u9898\u7684\u4fe1\u606f\u4e0d\u8db3\uff0c\u53e6\u4e00\u4e9b\u95ee\u9898\u7684\u6d4b\u8bd5\u8fc7\u4e8e\u4e25\u683c\u3002\u201d<\/p>\n<p><a href=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-5ae3197cd1ba271ff3cb442eb7f80af8.png\" data-fancybox=\"images\" data-fancybox=\"gallery\"><img decoding=\"async\" src=\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-5ae3197cd1ba271ff3cb442eb7f80af8.png\"><\/a><\/p>\n<p><strong>SWE-bench Lite-S\uff1a\u7ecf\u8fc7\u8fc7\u6ee4\u7684\u4e25\u683c\u95ee\u9898\u5b50\u96c6<\/strong><\/p>\n<p>\u9488\u5bf9\u8fd9\u4e9b\u95ee\u9898\uff0c\u7814\u7a76\u8005\u63d0\u51fa\u4e86\u4e00\u4e2a\u4e25\u683c\u7684\u95ee\u9898\u5b50\u96c6 SWE-bench Lite-S\uff08\u5305\u542b 252 \u4e2a\u95ee\u9898\uff09\u3002\u5177\u4f53\u6765\u8bf4\uff0c\u4ece SWE-bench Lite\uff08\u5305\u542b 300 \u4e2a\u95ee\u9898\uff09\u4e2d\u6392\u9664\u4e86\u90a3\u4e9b\u5728\u95ee\u9898\u63cf\u8ff0\u4e2d\u5305\u542b\u786e\u5207\u8865\u4e01\u3001\u8bef\u5bfc\u6027\u89e3\u51b3\u65b9\u6848\u6216\u672a\u63d0\u4f9b\u8db3\u591f\u4fe1\u606f\u7684\u95ee\u9898\u3002\u8fd9\u6837\u53ef\u4ee5\u53bb\u9664\u4e0d\u5408\u7406\u7684\u95ee\u9898\uff0c\u5e76\u4f7f<mark data-type=\"concepts\" data-id=\"308c3a45-0fee-4ec6-858e-85b15f440fc0\">\u57fa\u51c6<\/mark>\u6d4b\u8bd5\u7684\u96be\u5ea6\u6c34\u5e73\u6807\u51c6\u5316\u3002\u4e0e\u539f\u59cb\u7684 SWE-bench Lite \u76f8\u6bd4\uff0c\u8fc7\u6ee4\u540e\u7684<mark data-type=\"concepts\" data-id=\"308c3a45-0fee-4ec6-858e-85b15f440fc0\">\u57fa\u51c6<\/mark>\u6d4b\u8bd5\u66f4\u51c6\u786e\u5730\u53cd\u6620\u4e86\u81ea\u52a8\u8f6f\u4ef6\u5f00\u53d1\u5de5\u5177\u7684\u771f\u5b9e\u80fd\u529b\u3002<\/p>\n<p><strong>\u7ed3\u8bed<\/strong><\/p>\n<p>\u5c3d\u7ba1\u57fa\u4e8e Agent \u7684\u8f6f\u4ef6\u5f00\u53d1\u975e\u5e38\u6709\u524d\u666f\uff0c\u4f5c\u8005\u4eec\u8ba4\u4e3a\u6280\u672f\u548c\u7814\u7a76\u793e\u533a\u662f\u65f6\u5019\u505c\u4e0b\u6765\u601d\u8003\u5176\u5173\u952e\u8bbe\u8ba1\u4e0e\u8bc4\u4f30\u65b9\u6cd5\uff0c\u800c\u4e0d\u662f\u6025\u4e8e\u53d1\u5e03\u66f4\u591a\u7684 Agent\u3002\u7814\u7a76\u8005\u5e0c\u671b Agentless \u53ef\u4ee5\u5e2e\u52a9\u91cd\u7f6e\u672a\u6765\u8f6f\u4ef6\u5de5\u7a0b Agent \u7684\u57fa\u7ebf\u548c\u65b9\u5411\u3002<\/p>\n<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:<a href=\"https:\/\/www.jiqizhixin.com\/articles\/2024-07-15-12\" target=\"_blank\">\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u699c\u9996\uff0cUIUC\u65e0Agent\u65b9\u6848\u8f7b\u677e\u89e3\u51b3SWE-bench\u771f\u5b9e\u7f16\u7a0b\u95ee\u9898<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u6587\u7ae0\u6765\u6e90\u4e8e\u4e92\u8054\u7f51:\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08 [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[27],"tags":[70,68,55],"class_list":["post-34545","post","type-post","status-publish","format-standard","hentry","category-news","tag-agent","tag-68","tag-55"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u699c\u9996\uff0cUIUC\u65e0Agent\u65b9\u6848\u8f7b\u677e\u89e3\u51b3SWE-bench\u771f\u5b9e\u7f16\u7a0b\u95ee\u9898 - \u4e00\u8d77AI\u6280\u672f<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/17aitech.com\/?p=34545\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/17aitech.com\/?p=34545\",\"url\":\"https:\/\/17aitech.com\/?p=34545\",\"name\":\"\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u699c\u9996\uff0cUIUC\u65e0Agent\u65b9\u6848\u8f7b\u677e\u89e3\u51b3SWE-bench\u771f\u5b9e\u7f16\u7a0b\u95ee\u9898 - \u4e00\u8d77AI\u6280\u672f\",\"isPartOf\":{\"@id\":\"https:\/\/17aitech.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/17aitech.com\/?p=34545#primaryimage\"},\"image\":{\"@id\":\"https:\/\/17aitech.com\/?p=34545#primaryimage\"},\"thumbnailUrl\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0109fcad6d51c97f8f50d37f1fad6e2b.png\",\"datePublished\":\"2024-12-08T09:56:25+00:00\",\"author\":{\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d\"},\"breadcrumb\":{\"@id\":\"https:\/\/17aitech.com\/?p=34545#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/17aitech.com\/?p=34545\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/17aitech.com\/?p=34545#primaryimage\",\"url\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0109fcad6d51c97f8f50d37f1fad6e2b.png\",\"contentUrl\":\"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0109fcad6d51c97f8f50d37f1fad6e2b.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/17aitech.com\/?p=34545#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/17aitech.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u699c\u9996\uff0cUIUC\u65e0Agent\u65b9\u6848\u8f7b\u677e\u89e3\u51b3SWE-bench\u771f\u5b9e\u7f16\u7a0b\u95ee\u9898\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/17aitech.com\/#website\",\"url\":\"https:\/\/17aitech.com\/\",\"name\":\"\u4e00\u8d77AI\u6280\u672f\",\"description\":\"\u8ba9AI\u77e5\u8bc6\u89e6\u624b\u53ef\u53ca\",\"alternateName\":\"\u4e00\u8d77AI\u6280\u672f\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/17aitech.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d\",\"name\":\"AI\u5c0f\u52a9\u624b\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/17aitech.com\/#\/schema\/person\/image\/\",\"url\":\"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png\",\"contentUrl\":\"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png\",\"caption\":\"AI\u5c0f\u52a9\u624b\"},\"description\":\"\u8fd9\u4e2a\u4eba\u5f88\u61d2\uff0c\u4ec0\u4e48\u90fd\u6ca1\u6709\u7559\u4e0b\uff5e\",\"url\":\"https:\/\/17aitech.com\/?page_id=33738&user=3\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u699c\u9996\uff0cUIUC\u65e0Agent\u65b9\u6848\u8f7b\u677e\u89e3\u51b3SWE-bench\u771f\u5b9e\u7f16\u7a0b\u95ee\u9898 - \u4e00\u8d77AI\u6280\u672f","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/17aitech.com\/?p=34545","schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/17aitech.com\/?p=34545","url":"https:\/\/17aitech.com\/?p=34545","name":"\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u699c\u9996\uff0cUIUC\u65e0Agent\u65b9\u6848\u8f7b\u677e\u89e3\u51b3SWE-bench\u771f\u5b9e\u7f16\u7a0b\u95ee\u9898 - \u4e00\u8d77AI\u6280\u672f","isPartOf":{"@id":"https:\/\/17aitech.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/17aitech.com\/?p=34545#primaryimage"},"image":{"@id":"https:\/\/17aitech.com\/?p=34545#primaryimage"},"thumbnailUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0109fcad6d51c97f8f50d37f1fad6e2b.png","datePublished":"2024-12-08T09:56:25+00:00","author":{"@id":"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d"},"breadcrumb":{"@id":"https:\/\/17aitech.com\/?p=34545#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/17aitech.com\/?p=34545"]}]},{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/17aitech.com\/?p=34545#primaryimage","url":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0109fcad6d51c97f8f50d37f1fad6e2b.png","contentUrl":"https:\/\/17aitech.com\/wp-content\/uploads\/2024\/07\/frc-0109fcad6d51c97f8f50d37f1fad6e2b.png"},{"@type":"BreadcrumbList","@id":"https:\/\/17aitech.com\/?p=34545#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/17aitech.com\/"},{"@type":"ListItem","position":2,"name":"\u767b\u9876\u5f00\u6e90AI\u8f6f\u4ef6\u5de5\u7a0b\u5e08\u699c\u9996\uff0cUIUC\u65e0Agent\u65b9\u6848\u8f7b\u677e\u89e3\u51b3SWE-bench\u771f\u5b9e\u7f16\u7a0b\u95ee\u9898"}]},{"@type":"WebSite","@id":"https:\/\/17aitech.com\/#website","url":"https:\/\/17aitech.com\/","name":"\u4e00\u8d77AI\u6280\u672f","description":"\u8ba9AI\u77e5\u8bc6\u89e6\u624b\u53ef\u53ca","alternateName":"\u4e00\u8d77AI\u6280\u672f","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/17aitech.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/17aitech.com\/#\/schema\/person\/60225458499e817ae0af73e67e440b9d","name":"AI\u5c0f\u52a9\u624b","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/17aitech.com\/#\/schema\/person\/image\/","url":"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png","contentUrl":"\/\/17aitech.com\/wp-content\/uploads\/2024\/04\/robot_3.png","caption":"AI\u5c0f\u52a9\u624b"},"description":"\u8fd9\u4e2a\u4eba\u5f88\u61d2\uff0c\u4ec0\u4e48\u90fd\u6ca1\u6709\u7559\u4e0b\uff5e","url":"https:\/\/17aitech.com\/?page_id=33738&user=3"}]}},"_links":{"self":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/34545","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=34545"}],"version-history":[{"count":0,"href":"https:\/\/17aitech.com\/index.php?rest_route=\/wp\/v2\/posts\/34545\/revisions"}],"wp:attachment":[{"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=34545"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=34545"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/17aitech.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=34545"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}