{"author_url":"https://blog.hatena.ne.jp/fanta_orange_grape/","height":"190","version":"1.0","provider_name":"Hatena Blog","type":"rich","author_name":"fanta_orange_grape","description":"\u8ad6\u6587 arxiv.org \u6982\u8981\uff08\u5358\u306b\u8ad6\u6587\u306e\u6982\u8981\u306eChat\u65e5\u672c\u8a9e\u8a33\uff09 Weshowthat reinforcement learning applied to large language models (LLMs) significantly boosts performance on complex coding and reasoning tasks. Additionally, we compare two general-purpose reasoning models \u2014 OpenAI o1 and an early checkpoint of o3 \u2014 with a domain-\u2026","url":"https://ai-de-seikei.hatenablog.com/entry/2025/07/03/023953","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fai-de-seikei.hatenablog.com%2Fentry%2F2025%2F07%2F03%2F023953\" title=\"\u8ad6\u6587\u300eCompetitive Programming with Large Reasoning Models\u300f\u3092\u8aad\u3080\u3002 - AI\u3046\u3049\uff0d\uff0d\uff01(ai-wo-katsuyo-shitai !)\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","blog_url":"https://ai-de-seikei.hatenablog.com/","categories":[],"width":"100%","provider_url":"https://hatena.blog","title":"\u8ad6\u6587\u300eCompetitive Programming with Large Reasoning Models\u300f\u3092\u8aad\u3080\u3002","blog_title":"AI\u3046\u3049\uff0d\uff0d\uff01(ai-wo-katsuyo-shitai !)","published":"2025-07-03 02:39:53","image_url":null}