<?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>智能体评测 on AI 实战派 · 从技术到赚钱</title><link>https://guijiagi.com/tags/%E6%99%BA%E8%83%BD%E4%BD%93%E8%AF%84%E6%B5%8B/</link><description>Recent content in 智能体评测 on AI 实战派 · 从技术到赚钱</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Thu, 22 Oct 2026 10:42:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%99%BA%E8%83%BD%E4%BD%93%E8%AF%84%E6%B5%8B/index.xml" rel="self" type="application/rss+xml"/><item><title>「UCLA×Adobe的Tev：27B开源追平GPT-6 Astra」小模型凭什么打榜？</title><link>https://guijiagi.com/posts/2026-10-22-17-ucla-adobe-tev-27b-agent-benchmark/</link><pubDate>Thu, 22 Oct 2026 10:42:00 +0800</pubDate><guid>https://guijiagi.com/posts/2026-10-22-17-ucla-adobe-tev-27b-agent-benchmark/</guid><description>加州大学洛杉矶分校与Adobe提出Tev，先用27B开源模型造好答案世界，再用Tev-Gym给智能体出长程考题，据称在相关基准上追平GPT-6 Astra与Claude Opus 5。</description></item></channel></rss>