<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
    <channel>
        <title>强化学习 on vllbc02&#39;s blogs</title>
        <link>https://blog.vllbc.top/tags/%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0/</link>
        <description>Recent content in 强化学习 on vllbc02&#39;s blogs</description>
        <generator>Hugo -- gohugo.io</generator>
        <language>zh-cn</language>
        <lastBuildDate>Fri, 30 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.vllbc.top/tags/%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0/index.xml" rel="self" type="application/rss+xml" /><item>
            <title>GiGPO</title>
            <link>https://blog.vllbc.top/visual-reading/gigpo/</link>
            <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/gigpo/</guid>
            <description></description>
        </item><item>
            <title>Geometric-Mean Policy Optimization</title>
            <link>https://blog.vllbc.top/visual-reading/geopo/</link>
            <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/geopo/</guid>
            <description></description>
        </item><item>
            <title>Parallel-R1</title>
            <link>https://blog.vllbc.top/visual-reading/parallel-r1/</link>
            <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/parallel-r1/</guid>
            <description></description>
        </item><item>
            <title>CAPO</title>
            <link>https://blog.vllbc.top/visual-reading/capo/</link>
            <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/capo/</guid>
            <description></description>
        </item><item>
            <title>UloRL</title>
            <link>https://blog.vllbc.top/visual-reading/ulorl/</link>
            <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/ulorl/</guid>
            <description></description>
        </item><item>
            <title>RLVMR</title>
            <link>https://blog.vllbc.top/visual-reading/rlvmr/</link>
            <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/rlvmr/</guid>
            <description></description>
        </item><item>
            <title>Understanding Tool-Integrated Reasoning</title>
            <link>https://blog.vllbc.top/visual-reading/understanding-tool-integrated-reasoning/</link>
            <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/understanding-tool-integrated-reasoning/</guid>
            <description></description>
        </item><item>
            <title>Code-Integrated Reasoning</title>
            <link>https://blog.vllbc.top/visual-reading/code-integrated-reasoning/</link>
            <pubDate>Fri, 30 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/code-integrated-reasoning/</guid>
            <description></description>
        </item><item>
            <title>LAPO</title>
            <link>https://blog.vllbc.top/visual-reading/lapo/</link>
            <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/lapo/</guid>
            <description></description>
        </item><item>
            <title>Train Long, Think Short</title>
            <link>https://blog.vllbc.top/visual-reading/train-long-think-short/</link>
            <pubDate>Fri, 30 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/train-long-think-short/</guid>
            <description></description>
        </item><item>
            <title>Beyond Ten Turns</title>
            <link>https://blog.vllbc.top/visual-reading/beyond-ten-turns/</link>
            <pubDate>Thu, 29 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/beyond-ten-turns/</guid>
            <description></description>
        </item><item>
            <title>Memory-R1</title>
            <link>https://blog.vllbc.top/visual-reading/memory-r1/</link>
            <pubDate>Fri, 30 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/memory-r1/</guid>
            <description></description>
        </item><item>
            <title>Beyond Correctness</title>
            <link>https://blog.vllbc.top/visual-reading/beyond-correctness/</link>
            <pubDate>Fri, 30 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/beyond-correctness/</guid>
            <description></description>
        </item><item>
            <title>SSRL</title>
            <link>https://blog.vllbc.top/visual-reading/ssrl/</link>
            <pubDate>Fri, 30 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/ssrl/</guid>
            <description></description>
        </item><item>
            <title>ZeroSearch</title>
            <link>https://blog.vllbc.top/visual-reading/zerosearch/</link>
            <pubDate>Fri, 30 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/zerosearch/</guid>
            <description></description>
        </item><item>
            <title>VAPO</title>
            <link>https://blog.vllbc.top/visual-reading/vapo/</link>
            <pubDate>Fri, 30 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/vapo/</guid>
            <description></description>
        </item><item>
            <title>SFR-DeepResearch</title>
            <link>https://blog.vllbc.top/visual-reading/sfr-deepresearch/</link>
            <pubDate>Fri, 30 Oct 2026 00:00:00 +0000</pubDate>
            <guid>https://blog.vllbc.top/visual-reading/sfr-deepresearch/</guid>
            <description></description>
        </item></channel>
</rss>
