HOT RADAR
llmHEAT 13.9°

AI CURATED HOT STORY · 11/11/2026

MBZUAI Releases PAN 2 Open World Model for Simulative Reasoning

1 reports archived1 independent sourcesupdated 11/11/2026, 02:20:58
Synthesis & Latest Updates
1 Sources Cross-Validated

MBZUAI's Institute of Foundation Models released PAN 2, an open foundation world model for physical intelligence built around simulative reasoning that lets agents play out outcomes before acting. It splits reasoning into two tracks: an LLM determines what happens, when, and how the camera moves and writes it as text, while a 29B diffusion model trained from scratch renders that text into visuals. Ablating the LLM collapses multi-step performance to 8.7% correct steps with no completed plans, whereas the combined system reaches 75.1% correct steps and 34.0% fully completed plans.

LATEST/MBZUAI's Institute of Foundation Models released PAN 2, an open foundation world model for physical intelligence built around simulative reasoning that lets agents play out outcomes before acting. It splits reasoning into two tracks: an LLM determines what happens, when, and how the camera moves and writes it as text, while a 29B diffusion model trained from scratch renders that text into visuals. Ablating the LLM collapses multi-step performance to 8.7% correct steps with no completed plans, whereas the combined system reaches 75.1% correct steps and 34.0% fully completed plans.

Hourly heat curve

2 fully observed hours
Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first
  1. Rohan Paul (@rohanpaul_ai)T2·78 pts
    • PAN 2 splits world-model reasoning into conceptual planning via an LLM and perceptual rendering via a 29B diffusion model
    • Removing the LLM drops multi-step performance to 8.7% correct steps with zero completed plans, showing action ordering depends on the language model
    • The combined system reaches 75.1% correct steps and 34.0% fully completed plans, the best among models IFM tested