<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Protocol on AI Agents News</title>
    <link>https://aiagentsnews.top/tags/protocol/</link>
    <description>Recent content in Protocol on AI Agents News</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Fri, 24 Jul 2026 12:08:10 +0000</lastBuildDate>
    <atom:link href="https://aiagentsnews.top/tags/protocol/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Function calling tools: 24 benchmarks explained</title>
      <link>https://aiagentsnews.top/posts/function-calling-tools-24-benchmarks-explained/</link>
      <pubDate>Sat, 18 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/function-calling-tools-24-benchmarks-explained/</guid>
      <description>BenchLM.ai evaluates function calling across 24 agentic benchmarks to measure precision in tool invocation and terminal task execution for AI agents.</description>
    </item>
    <item>
      <title>AGUI protocol on Bedrock: Stream agents via SSE</title>
      <link>https://aiagentsnews.top/posts/agui-protocol-on-bedrock-stream-agents-via-sse/</link>
      <pubDate>Tue, 14 Jul 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/agui-protocol-on-bedrock-stream-agents-via-sse/</guid>
      <description>Discover how to configure your container on port 8080 to stream SSE events and separate agent logic from frontend rendering with AGUI.</description>
    </item>
    <item>
      <title>OpenEnv: The Agentic-RL Standard That Won&#39;t Own Your Rewards</title>
      <link>https://aiagentsnews.top/posts/openenv-protocol-stop-agent-training-lock-in/</link>
      <pubDate>Mon, 15 Jun 2026 00:00:00 +0000</pubDate>
      <author>AI Agents News Editorial</author>
      <guid>https://aiagentsnews.top/posts/openenv-protocol-stop-agent-training-lock-in/</guid>
      <description>OpenEnv went to a 10-org committee and shrank to a pure interop socket, refusing to own rewards. Why that bet is smart, where it can still fail, and what to do </description>
    </item>
  </channel>
</rss>
