{"id":7423,"date":"2025-09-17T06:08:00","date_gmt":"2025-09-16T21:08:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7423"},"modified":"2025-09-14T09:11:16","modified_gmt":"2025-09-14T00:11:16","slug":"agentgym-rl-training-llm-agents-for-long-horizon-decision-making-through-multi-turn-reinforcement-learning","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7423","title":{"rendered":"\ufeffAgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning\u00a0<\/strong>[129.4]<br>\u672c\u7a3f\u3067\u306f,\u30de\u30eb\u30c1\u30bf\u30fc\u30f3\u5bfe\u8a71\u578b\u610f\u601d\u6c7a\u5b9a\u306e\u305f\u3081\u306eLLM\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u3092RL\u3067\u5b66\u7fd2\u3059\u308b\u65b0\u3057\u3044\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u3067\u3042\u308bAgentGym-RL\u3092\u7d39\u4ecb\u3059\u308b\u3002 \u672c\u7814\u7a76\u3067\u306f,\u63a2\u7d22-\u63a2\u7d22\u30d0\u30e9\u30f3\u30b9\u3068\u5b89\u5b9a\u3057\u305fRL\u6700\u9069\u5316\u306e\u305f\u3081\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u624b\u6cd5\u3067\u3042\u308bScalingInter-RL\u3092\u63d0\u6848\u3059\u308b\u3002 \u5f53\u793e\u306e\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306f\u3001\u3055\u307e\u3056\u307e\u306a\u74b0\u5883\u306b\u307e\u305f\u304c\u308b27\u306e\u30bf\u30b9\u30af\u3067\u3001\u5546\u7528\u30e2\u30c7\u30eb\u306b\u30de\u30c3\u30c1\u3059\u308b\u304b\u3001\u8d85\u3048\u3066\u3044\u307e\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2509.08755v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2509.08755v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Wed, 10 Sep 2025 16:46:11 GMT)<\/li>\n\n\n\n<li>\u69d8\u3005\u306a\u5f37\u5316\u5b66\u7fd2\u306e\u30a2\u30d7\u30ed\u30fc\u30c1\u306b\u5bfe\u5fdc\u3057\u305f\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af<\/li>\n\n\n\n<li>\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30b5\u30a4\u30c8\u306f<a href=\"https:\/\/agentgym-rl.github.io\/\">AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning<\/a>\u3001\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/WooooDyy\/AgentGym-RL\">GitHub &#8211; WooooDyy\/AgentGym-RL: Code and implementations for the paper &#8220;AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning&#8221; by Zhiheng Xi et al.<\/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":[307,576],"class_list":["post-7423","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-post-training","tag-576"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7423","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=7423"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7423\/revisions"}],"predecessor-version":[{"id":7424,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7423\/revisions\/7424"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7423"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7423"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7423"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}