{"id":6610,"date":"2025-04-24T04:35:00","date_gmt":"2025-04-23T19:35:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6610"},"modified":"2025-04-24T04:35:00","modified_gmt":"2025-04-23T19:35:00","slug":"exploring-expert-failures-improves-llm-agent-tuning","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6610","title":{"rendered":"Exploring Expert Failures Improves LLM Agent Tuning"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Exploring Expert Failures Improves LLM Agent Tuning\u00a0<\/strong>[76.3]<br>\u672c\u7a3f\u3067\u306f,\u5931\u6557\u3057\u305f\u5c02\u9580\u5bb6\u306e\u8ecc\u9053\u304b\u3089\u6709\u76ca\u306a\u884c\u52d5\u3092\u8b58\u5225\u3059\u308b\u5c02\u9580\u7684\u5931\u6557\u306e\u63a2\u7d22(EEF)\u3092\u63d0\u6848\u3059\u308b\u3002 EEF\u306f\u3001\u672a\u89e3\u6c7a\u306e\u3044\u304f\u3064\u304b\u306e\u30b5\u30d6\u30bf\u30b9\u30af\u3092\u3046\u307e\u304f\u89e3\u6c7a\u3057\u3001\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u6027\u80fd\u3092\u6539\u5584\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2504.13145v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2504.13145v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 17 Apr 2025 17:53:54 GMT)<\/li>\n\n\n\n<li>\u300cIn this paper, we present EEF, a novel framework that learns beneficial actions from negative expert data while remaining robust against noise from suboptimal actions.\u300d\u3001WebShop\u3068 SciWorld\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067SoTA\u3092\u4e3b\u5f35<\/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],"class_list":["post-6610","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-autonomous-agent"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6610","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=6610"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6610\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6610"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6610"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6610"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}