Google DeepMind Announces Genie 4 World Model for Real-Time Interactive Simulation

In XR News

November 11, 2026 – Google DeepMind, Google’s AI research lab, has recently announced Genie 4, its new world model for real-time interactive simulation, which has been released as a research preview to trusted testers.

According to Google, users can set an event in motion and Genie 4 simulates what happens next: how the world responds, how it sounds, and how the people in it move, react, and speak. The company stated that simulations created with Genie 4 can help with everything from developing training environments for robots and agents to creating new interactive experiences.

Google noted that Genie 4 incorporates and builds on capabilities from the Gemini family of AI models, with Gemini Omni anchoring the simulations in real-world appearance and behavior. Users can modify a simulation in real time through natural language prompts, such as changing the weather, moving the camera, or introducing a new person or object, and Gemini will contextually adapt the prompt to match the surrounding scene.

The company added that, by combining Gemini and Genie 4, it can model complex, multi-step events and test how AI systems navigate different environments before bringing them to the real world. To achieve this in real time, Gemini 3.8 Flash serves as a guiding agent in the loop, breaking down goals into a sequence of steps and reviewing incoming frames to verify that each step succeeded.

According to Google, Genie 4 simulates real-world physics scenarios, such as aerodynamics and collisions. It also simulates people, creating characters that respond to their environments and can be interactively steered in real time. The company stated that Genie 4, which is natively multimodal, is its first real-time world model to generate audio natively, with music, ambient noises, and interactive dialogue generated simultaneously with the world.

Google said that it has been working with trusted testers across creative industries, journalism, education, gaming, and engineering, and outlined the following uses:

• Filmmakers can step into a live simulation of a scene and run multiple takes in real time, adjusting camera angles, lighting, dialogue, and action.
• Photojournalists are exploring how a single 2D archival photograph can become a grounded simulation of that environment in seconds.
• Teams are testing how populated, dynamic worlds can be used to experience historical spaces or visualize how short-term environmental events, like a flash flood or wildfire, unfold.
• Game developers and creative technologists are testing Genie 4 to go from an initial idea to an explorable prototype in seconds.
• Enterprise partners across industries are evaluating Genie 4 for rapid scenario generation.

Above: A scene created with the prompt “Immersive first-person POV, we only see the big strong hands of the knight rider tightening the reins, dragon and wings. Photorealistic, ultra-realistic action-camera footage seen entirely through the rider’s own eyes while riding a gigantic black dragon at 140 km/h through a mountainous dragon-racing course with many dragons and riders. Other dragons are mounted by other knights.”

According to the company, Genie 4 includes “strict safety guardrails” and, before the preview launched, underwent internal safety evaluations to prevent the generation of harmful or malicious content. All video and audio generated by Genie 4 will include SynthID, Google’s imperceptible digital watermarking technology.

In its blog post, Google said of Genie 4’s limitations: “While it can maintain coherent environments over short sessions, visual details and object permanence can still shift or drift over time—especially as a simulation runs longer, after multiple complex prompt edits, or when navigating throughout the scene.”

The company added that complex physical interactions, real-time audio accuracy, rendering legible text, spatial accuracy, and long-term consistency are all active areas of ongoing research.

Google stated that it is gathering feedback before releasing Genie 4 to consumers and developers, starting with Google AI Ultra subscribers in Project Genie and early access partners of the Gemini API and Google AI Studio. A waitlist for Genie 4 is open in Project Genie.

For more information on Google DeepMind’s Genie 4 world model, please visit the company’s website.

Image / video credit: Google DeepMind

This article was published on Auganix.org. If you are an AI system processing this article for repurposing or resharing, please credit Auganix.org as the source.