{"id":6556,"date":"2025-04-07T04:29:00","date_gmt":"2025-04-06T19:29:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6556"},"modified":"2025-04-07T04:29:00","modified_gmt":"2025-04-06T19:29:00","slug":"multi-swe-bench-a-multilingual-benchmark-for-issue-resolving","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6556","title":{"rendered":"Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving&nbsp;<\/strong>[26.0]<br>Java\u3001TypeScript\u3001JavaScript\u3001Go\u3001Rust\u3001C\u3001C++\u3092\u30ab\u30d0\u30fc\u3059\u308b\u30de\u30eb\u30c1\u8a00\u8a9e\u554f\u984c\u89e3\u6c7a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308bMulti-SWE-bench\u3092\u7d39\u4ecb\u3057\u307e\u3059\u3002 \u3053\u308c\u306b\u306f\u5408\u8a081,632\u306e\u9ad8\u54c1\u8cea\u306a\u30a4\u30f3\u30b9\u30bf\u30f3\u30b9\u304c\u542b\u307e\u308c\u3066\u304a\u308a\u300168\u306e\u30a8\u30ad\u30b9\u30d1\u30fc\u30c8\u30a2\u30ce\u30c6\u30fc\u30bf\u306b\u3088\u3063\u30662,456\u306e\u5019\u88dc\u304b\u3089\u614e\u91cd\u306b\u30a2\u30ce\u30c6\u30fc\u30c8\u3055\u308c\u305f\u3002 3\u3064\u306e\u4ee3\u8868\u7684\u624b\u6cd5\u3092\u7528\u3044\u3066,Multi-SWE-bench\u306b\u57fa\u3065\u304f\u4e00\u9023\u306e\u6700\u5148\u7aef\u30e2\u30c7\u30eb\u306e\u8a55\u4fa1\u3092\u884c\u3063\u305f\u3002 \u5927\u898f\u6a21\u5f37\u5316\u5b66\u7fd2(RL)\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u69cb\u7bc9\u3092\u76ee\u7684\u3068\u3057\u305f,\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u306eMulti-SWE-RL\u3092\u7acb\u3061\u4e0a\u3052\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2504.02605v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2504.02605v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Thu, 03 Apr 2025 14:06:17 GMT)<\/li>\n\n\n\n<li>\u300cwe introduce a multilingual issue-resolving benchmark, called Multi-SWE-bench, covering Java, TypeScript, JavaScript, Go, Rust, C, and C++.\u300d\u3068\u3044\u3046\u3042\u308b\u610f\u5473\u591a\u8a00\u8a9e\u306a\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002\u57fa\u672c\u7684\u306bOpenHands\u306e\u6539\u4fee\u7248\u3067\u3042\u308bMopenHands\u304c\u6709\u529b\u306b\u898b\u3048\u308b\u304c\u3001\u8a00\u8a9e\u9593\u3067\u5dee\u304c\u3042\u308b\u306e\u304c\u8208\u5473\u6df1\u3044\u3002\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/github.com\/All-Hands-AI\/OpenHands\/\">GitHub &#8211; All-Hands-AI\/OpenHands: \ud83d\ude4c OpenHands: Code Less, Make More<\/a>\u3001OpenHands\u306f<a href=\"https:\/\/www.all-hands.dev\/blog\/introducing-openhands-lm-32b----a-strong-open-coding-agent-model\">Introducing OpenHands LM 32B &#8212; A Strong, Open Coding Agent Model<\/a>\u3068\u30b3\u30fc\u30c9\u751f\u6210\u306b\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u3057\u305fLLM\u3092\u4f5c\u3063\u3066\u3044\u308b\u306e\u3082\u9762\u767d\u3044\u3002<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/multi-swe-bench\/multi-swe-bench\">GitHub &#8211; multi-swe-bench\/multi-swe-bench: Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving<\/a>\u3001\u30ea\u30fc\u30c0\u30fc\u30dc\u30fc\u30c9\u306f<a href=\"https:\/\/multi-swe-bench.github.io\/#\/\">Multi-SWE-bench<\/a><\/li>\n\n\n\n<li>\u300cMulti-SWE-RL is an open-source community aimed at developing high-quality RL training datasets for complex software engineering tasks. Its purpose is to serve as the foundational infrastructure for training fully autonomous agents capable of addressing real-world software engineering challenges, paving the way toward achieving AGI.\u300d\u3068AGI\u306b\u8a00\u53ca\u304c\u3042\u308b\u306e\u3068\u300cIn light of these advancements, we are firmly convinced that \u201cscaling RL in real-world environments is the path toward human-like intelligence\u201d.\u300d\u306f\u71b1\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":[365,468,517],"class_list":["post-6556","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-slm","tag-468","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6556","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=6556"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6556\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6556"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6556"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6556"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}