We current SWE-Fitness center, the primary setting for coaching real-world software program engineering (SWE) brokers. SWE-Fitness center incorporates 2,438 real-world Python process situations, every comprising a codebase with an executable runtime setting, unit exams, and a process laid out in pure language. We use SWE-Fitness center to coach language mannequin primarily based SWE brokers, reaching as much as 19% absolute good points in resolve price on the favored SWE-Bench Verified and Lite check units. We additionally experiment with inference-time scaling by verifiers educated on agent trajectories sampled from SWE-Fitness center. When mixed with our fine-tuned SWE brokers, we obtain 32.0% and 26.0% on SWE-Bench Verified and Lite, respectively, reflecting a brand new state-of-the-art for open-weight SWE brokers. To facilitate additional analysis, we publicly launch SWE-Fitness center, fashions, and agent trajectories.<\/p>\n

* Equal contribution<\/li>\n
\u2020 College of California, Berkeley<\/li>\n
\u2021 Work executed whereas at Apple<\/li>\n
\u00a7 College of Illinois Urbana-Champaign<\/li>\n
\u00b6 Carnegie Mellon College<\/li>\n<\/ul>\n<\/div>\n\n","protected":false},"excerpt":{"rendered":"
We current SWE-Fitness center, the primary setting for coaching real-world software program engineering (SWE) brokers. SWE-Fitness center incorporates 2,438 real-world Python process situations, every comprising a codebase with an executable runtime setting, unit exams, and a process laid out in pure language. We use SWE-Fitness center to coach language mannequin primarily based SWE brokers, reaching […]<\/p>\n","protected":false},"author":2,"featured_media":8009,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[55],"tags":[617,2060,802,6074,2401,6073],"class_list":["post-8007","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-learning","tag-agents","tag-engineering","tag-software","tag-swegym","tag-training","tag-verifiers"],"_links":{"self":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/8007","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=8007"}],"version-history":[{"count":1,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/8007\/revisions"}],"predecessor-version":[{"id":8008,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/8007\/revisions\/8008"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/media\/8009"}],"wp:attachment":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8007"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8007"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8007"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}