Skip to content
ThreadOut
Google DeepMind@GoogleDeepMind · Nov 13, 2025

SIMA 2 is our most capable AI agent for virtual 3D worlds. 👾🌐 Powered by Gemini, it goes beyond following basic…

5 tweets1 min read♥ 6.4Koriginal

Summary

Google announced SIMA 2, an advanced AI agent powered by Gemini that can understand and act in 3D virtual worlds with improved reasoning, generalization to unseen environments, and self-teaching capabilities. The system represents progress toward more capable AI agents with potential applications in robotics and real-world AGI development.

Summarized by ThreadOut AI from the full thread. May miss nuance — read the thread below.

  1. #1

    SIMA 2 is our most capable AI agent for virtual 3D worlds. 👾🌐 Powered by Gemini, it goes beyond following basic instructions to think, understand, and take actions in interactive environments – meaning you can talk to it through text, voice, or even images. Here’s how 🧵

  2. #2

    Advanced reasoning 🧠 We trained SIMA 2 to achieve high-level goals in a wide array of games – allowing it to perform complex reasoning and independently plan how to accomplish tasks. It acts like a collaborative partner that can explain its intentions and answer questions about its behavior.

  3. #3

    Generalization ☂️ SIMA 2 is now far better at carrying out detailed instructions, even in worlds it's never seen before. It can transfer learned concepts like “mining” in one game and apply it to “harvesting” in another – connecting the dots between similar tasks. It even navigated unseen environments created in real-time by our Genie 3 model.

  4. #4

    Self-improvement 🔄 SIMA 2 can teach itself new skills, learning through trial-and-error, based on feedback from Gemini. Getting better the more it plays – without additional human input.

  5. #5

    Our SIMA 2 research offers a strong path towards applications in robotics and another step towards AGI in the real world. Find out more → goo.gle/SIMA-2