<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>工具调用 on Jiaqi</title>
    <link>https://blog.jiaqiguo.xyz/tags/%E5%B7%A5%E5%85%B7%E8%B0%83%E7%94%A8/</link>
    <description>Recent content in 工具调用 on Jiaqi</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Sun, 19 Jul 2026 18:30:00 +0800</lastBuildDate>
    <atom:link href="https://blog.jiaqiguo.xyz/tags/%E5%B7%A5%E5%85%B7%E8%B0%83%E7%94%A8/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>从会思考、会用工具到会被评测：读懂 ReAct、Toolformer、AgentBench 与 AgentBoard</title>
      <link>https://blog.jiaqiguo.xyz/posts/llm-agent-four-papers/</link>
      <pubDate>Sun, 19 Jul 2026 18:30:00 +0800</pubDate>
      <guid>https://blog.jiaqiguo.xyz/posts/llm-agent-four-papers/</guid>
      <description>四篇论文串起 LLM Agent 的关键问题：ReAct 让推理与行动形成闭环，Toolformer 让模型自监督学习 API 调用，AgentBench 把 agent 放进八种环境考试，AgentBoard 再用进度率和轨迹诊断回答“究竟卡在哪里”。</description>
    </item>
  </channel>
</rss>
