--- id: "2026-07-06-mira-multiplayer-world-model" url: "https://postcutoff.com/e/2026-07-06-mira-multiplayer-world-model/" as_of: "2026-11-13T13:49:00+01:00" date: "2026-07-06" date_precision: day category: research importance: 2 confidence: high status: [Confirmed] sources: 6 editor: human editor human_review: null version: "2026-10-04" --- As of: 2026-11-13 13:49 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-07-06-mira-multiplayer-world-model/ # General Intuition and Kyutai release MIRA, a real-time multiplayer world model of Rocket League On 2026-07-06 General Intuition and Kyutai, working with Epic Games, released MIRA, a 5B-parameter latent diffusion world model that simulates four-player 2v2 Rocket League matches in real time at 20 fps on a single GPU, conditioned on every player's actions. The technical report calls it the first multiplayer world model for highly dynamic physical interaction. Code (Apache-2.0), a 1,000-hour dataset slice and a playable demo were released. ## Key facts - 5B-parameter latent diffusion transformer plus a ~600M video codec built on frozen DINOv3-L representations; 20 fps, 576p split across four player views, single B200 GPU - Trained on ~10,000 match-hours of synthetic 2v2 gameplay from four instances of the public Nexto bot, with recorded actions - Distributional quality holds steady out to 5 minutes (longest measured); practical rollouts run for hours without diverging - Action dropout lets it run with 1 to 4 human players, with the model auto-piloting the rest - Released: training and inference code (Apache-2.0), Rocket Science dataset on Hugging Face, technical report arXiv 2607.05352, live demo at mira-wm.com - Known weaknesses: replays, hidden or off-screen information, out-of-distribution situations ## What happened General Intuition (the world-model lab spun out of the Medal game-clip platform) and the Paris lab Kyutai trained a world model that stands in for a game engine. Four people can play a full Rocket League match inside it: cars drive, hit the ball and score, and each view stays consistent with the others. ## Why it matters Most interactive world models (Genie 3, Oasis) simulate one agent. MIRA conditions on several action streams at once and attributes changes to the right player. Its authors frame this as a step toward physical AI (robots, autonomous vehicles), which need world models of many interacting agents. It is also a rare fully open, real-time world model release. The "first multiplayer world model" claim is the authors' own. ## Your AI and this story - GPT-6 Astra (training cutoff April 2026): 67 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 6 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 97 days after its cutoff - Grok 4.7 (training cutoff May 2026): 36 days after its cutoff ## Sources 1. [MIRA blog post](https://mira-wm.com/blog-post/) (mira-wm.com, official) 2. [arXiv 2607.05352: MIRA — Multiplayer Interactive World Models with Representation Autoencoders](https://arxiv.org/abs/2607.05352) (arxiv.org, paper) 3. [GitHub: mira-wm/mira](https://github.com/mira-wm/mira) (github.com, code) 4. [Hugging Face: kyutai/rocket-science dataset](https://huggingface.co/datasets/kyutai/rocket-science) (huggingface.co, code) 5. [Kyutai on X: introducing MIRA](https://x.com/kyutai_labs/status/2074104480178503943) (x.com, official) 6. [General Intuition on X](https://x.com/gen_intuition/status/2074104524596457706) (x.com, official) ## Changes - 2026-09-29 (filed): Created ## Related - 2026-01-29: [Google DeepMind opens Project Genie, a Genie 3 world-model prototype, to AI Ultra subscribers](https://postcutoff.com/e/2026-01-29-project-genie/index.md) - 2025-08-05: [Google DeepMind's Genie 3 generates interactive worlds in real time](https://postcutoff.com/e/2025-08-05-genie-3/index.md) - Archived: 2 posts, listed in https://postcutoff.com/e/2026-07-06-mira-multiplayer-world-model/index.json