{"id":7039,"date":"2025-07-08T05:09:00","date_gmt":"2025-07-07T20:09:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7039"},"modified":"2025-07-06T09:13:23","modified_gmt":"2025-07-06T00:13:23","slug":"establishing-best-practices-for-building-rigorous-agentic-benchmarks","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7039","title":{"rendered":"Establishing Best Practices for Building Rigorous Agentic Benchmarks\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Establishing Best Practices for Building Rigorous Agentic Benchmarks\u00a0<\/strong>[94.7]<br>\u591a\u304f\u306e\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u306f\u30bf\u30b9\u30af\u8a2d\u5b9a\u3084\u5831\u916c\u8a2d\u8a08\u304c\u554f\u984c\u3068\u306a\u3063\u3066\u3044\u308b\u3002 \u3053\u306e\u3088\u3046\u306a\u554f\u984c\u306f\u3001\u76f8\u5bfe\u7684\u306a\u7528\u8a9e\u3067\u3001\u904e\u5c0f\u8a55\u4fa1\u307e\u305f\u306f\u904e\u5927\u8a55\u4fa1\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u6700\u5927100%\u5411\u4e0a\u3055\u305b\u308b\u53ef\u80fd\u6027\u304c\u3042\u308b\u3002 \u6211\u3005\u306f\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u69cb\u7bc9\u7d4c\u9a13\u304b\u3089\u8981\u7d04\u3057\u305f\u30ac\u30a4\u30c9\u30e9\u30a4\u30f3\u306e\u96c6\u5408\u3067\u3042\u308bAgentic Benchmark Checklist (ABC)\u3092\u7d39\u4ecb\u3057\u305f\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2507.02825v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2507.02825v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 03 Jul 2025 17:35:31 GMT)<\/li>\n\n\n\n<li>\u69cb\u7bc9\u304c\u96e3\u3057\u3044\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u7cfb\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u306e\u6ce8\u610f\u70b9\u3092\u307e\u3068\u3081\u305f\u8ad6\u6587\u3002<\/li>\n\n\n\n<li>\u300cthe issues found in \u03c4-bench-Airline, some other example issues we found are: (1) an agent can score 100% on SWE-Lancer without resolving any tasks;\u300d\u306e\u3088\u3046\u306a\u554f\u984c\u306f\u76f8\u5fdc\u306b\u3042\u308b\u6c17\u304c\u3059\u308b\u3057\u3001\u300cBased on ABC, we assessed ten widely used agentic benchmarks and identified significant evaluation issues that cases up to 100% errors (in relative terms) when estimating agents\u2019 performance.\u300d\u3082\u9a5a\u6115\u3068\u3044\u3046\u611f\u3058\u3067\u306f\u306a\u3044\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/uiuc-kang-lab\/agentic-benchmarks\">GitHub &#8211; uiuc-kang-lab\/agentic-benchmarks<\/a><\/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":[42,517,648],"class_list":["post-7039","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent","tag-517","tag-648"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7039","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=7039"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7039\/revisions"}],"predecessor-version":[{"id":7040,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7039\/revisions\/7040"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7039"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7039"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7039"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}