<?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>Agent on Bluue Whale</title><link>https://bluuewhale.github.io/tags/agent/</link><description>Recent content in Agent on Bluue Whale</description><image><title>Bluue Whale</title><url>https://bluuewhale.github.io/images/profile.jpg</url><link>https://bluuewhale.github.io/images/profile.jpg</link></image><generator>Hugo -- 0.152.2</generator><language>en-us</language><lastBuildDate>Sat, 22 Aug 2026 22:21:36 +0900</lastBuildDate><atom:link href="https://bluuewhale.github.io/tags/agent/index.xml" rel="self" type="application/rss+xml"/><item><title>SIMA: A Generalist AI Agent for 3D Virtual Environments</title><link>https://bluuewhale.github.io/posts/sima-generalist-ai-agent-3d-environments-en/</link><pubDate>Sun, 16 Nov 2025 09:20:13 +0900</pubDate><guid>https://bluuewhale.github.io/posts/sima-generalist-ai-agent-3d-environments-en/</guid><description>How DeepMind&amp;#39;s SIMA plays multiple 3D games through nothing but screen pixels and keyboard/mouse output, trained with behavior cloning and classifier-free guidance.</description></item></channel></rss>