<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Intel</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Intel feed</description>
    <item>
      <title>Intel DeepMath Introduces a Smart Architecture to Make LLMs Better at Math</title>
      <link>https://www.infoq.com/news/2026/01/intel-deepmath-llm-architecture/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Intel</link>
      <description>&lt;img src="https://res.infoq.com/news/2026/01/intel-deepmath-llm-architecture/en/headerimage/intel-deepmath-1767636786834.jpeg"/&gt;&lt;p&gt;Intel has announced DeepMath, a lightweight agent built on Qwen3-Thinking that specializes in solving mathematical problems. To address common limitations of LLMs in math reasoning, DeepMath generates small Python scripts that support and enhance its problem-solving process.&lt;/p&gt; &lt;i&gt;By Sergio De Simone&lt;/i&gt;</description>
      <category>Large language models</category>
      <category>Python</category>
      <category>Agents</category>
      <category>Intel</category>
      <category>Development</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Mon, 05 Jan 2026 21:00:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2026/01/intel-deepmath-llm-architecture/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Intel</guid>
      <dc:creator>Sergio De Simone</dc:creator>
      <dc:date>2026-01-05T21:00:00Z</dc:date>
      <dc:identifier>/news/2026/01/intel-deepmath-llm-architecture/en</dc:identifier>
    </item>
  </channel>
</rss>
