{"author_url":"https://blog.hatena.ne.jp/joisino/","blog_title":"\uff7c\uff9e\uff6e\uff72\uff7c\uff9e\uff6e\uff72\uff7c\uff9e\uff6e\uff72","url":"https://joisino.hatenablog.com/entry/onedata","description":"\u63a8\u8ad6\u80fd\u529b\u3092\u9ad8\u3081\u308b\u305f\u3081\u306b\u306f\u3001LLM \u306e\u4e8b\u5f8c\u8a13\u7df4\u3067\u4f7f\u3046\u8a13\u7df4\u30c7\u30fc\u30bf\u306f 1 \u3064\u3067\u5341\u5206\u304b\u3082\u3057\u308c\u307e\u305b\u3093\u3002\u672c\u7a3f\u3067\u306f\u8a13\u7df4\u30c7\u30fc\u30bf\u3092 1 \u3064\u3060\u3051\u4f7f\u3063\u305f\u5f37\u5316\u5b66\u7fd2\u306b\u3064\u3044\u3066\u306e\u7814\u7a76 Reinforcement Learning for Reasoning in Large Language Models with One Training Example\uff08\u5358\u4e00\u306e\u8a13\u7df4\u4f8b\u3092\u7528\u3044\u305f\u5927\u898f\u6a21\u8a00\u8a9e\u30e2\u30c7\u30eb\u306b\u304a\u3051\u308b\u63a8\u8ad6\u306e\u305f\u3081\u306e\u5f37\u5316\u5b66\u7fd2, NeurIPS 2025\uff09\u306b\u3064\u3044\u3066\u89e3\u8aac\u3057\u307e\u3059\u3002 \u3053\u306e\u7814\u7a76\u306e\u7d50\u8ad6\u3092\u76f4\u89b3\u7684\u306b\u8ff0\u3079\u308b\u3068\u3001\u53b3\u9078\u3057\u305f\u6570\u5b66\u306e\u554f\u984c 1 \u554f\u306e\u89e3\u304d\u65b9\u3092 LLM \u306b\u3072\u305f\u3059\u3089\u8003\u3048\u3055\u305b\u7d9a\u3051\u308b\u3068\u9ad8\u3044\u63a8\u8ad6\u80fd\u529b\u304c\u5f97\u3089\u308c\u308b\u3068\u3044\u3046\u3053\u3068\u3067\u3059\u3002\u5f93\u6765\u306e\u8a13\u7df4\u2026","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fjoisino.hatenablog.com%2Fentry%2Fonedata\" title=\"\u8a13\u7df4\u30c7\u30fc\u30bf1\u500b\u3060\u3051\u3067LLM\u306e\u63a8\u8ad6\u6027\u80fd\u3092\u500d\u306b\u3059\u308b - \uff7c\uff9e\uff6e\uff72\uff7c\uff9e\uff6e\uff72\uff7c\uff9e\uff6e\uff72\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","categories":[],"width":"100%","provider_url":"https://hatena.blog","author_name":"joisino","title":"\u8a13\u7df4\u30c7\u30fc\u30bf1\u500b\u3060\u3051\u3067LLM\u306e\u63a8\u8ad6\u6027\u80fd\u3092\u500d\u306b\u3059\u308b","version":"1.0","type":"rich","blog_url":"https://joisino.hatenablog.com/","provider_name":"Hatena Blog","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/j/joisino/20251125/20251125152754.png","published":"2025-11-25 17:47:59","height":"190"}