<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>InfoQ - Microsoft Research - News</title>
    <link>https://www.infoq.com</link>
    <description>InfoQ Microsoft Research News feed</description>
    <item>
      <title>AI Agents Fail Manipulation Tests in Microsoft's Magentic Marketplace Simulation</title>
      <link>https://www.infoq.com/news/2025/11/magentic-marketplace-microsoft/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Microsoft+Research-news</link>
      <description>&lt;img src="https://res.infoq.com/news/2025/11/magentic-marketplace-microsoft/en/headerimage/generatedHeaderImage-1763349198746.jpg"/&gt;&lt;p&gt;Researchers at Microsoft, working in collaboration with Arizona State University, have introduced Magentic Marketplace, an open-source simulation environment designed to study how LLM-based agents behave in multi-agent economic systems. The platform addresses a growing need in AI research as autonomous agents gain capabilities in software development.&lt;/p&gt; &lt;i&gt;By Vinod Goje&lt;/i&gt;</description>
      <category>Agent2Agent</category>
      <category>Model Context Protocol (MCP)</category>
      <category>Microsoft Research</category>
      <category>Deep Learning</category>
      <category>Security Vulnerabilities</category>
      <category>Prompt Engineering</category>
      <category>AI, ML &amp; Data Engineering</category>
      <category>news</category>
      <pubDate>Thu, 20 Nov 2025 01:52:00 GMT</pubDate>
      <guid>https://www.infoq.com/news/2025/11/magentic-marketplace-microsoft/?utm_campaign=infoq_content&amp;utm_source=infoq&amp;utm_medium=feed&amp;utm_term=Microsoft+Research-news</guid>
      <dc:creator>Vinod Goje</dc:creator>
      <dc:date>2025-11-20T01:52:00Z</dc:date>
      <dc:identifier>/news/2025/11/magentic-marketplace-microsoft/en</dc:identifier>
    </item>
  </channel>
</rss>
