Critique of World Model

[Submitted on 7 Jul 2025 (v1), last revised 17 Jun 2026 (this version, v5)]

View PDF HTML (experimental)

Abstract:World Model, the algorithmic simulator of the real-world environment which biological agents experience and act upon, has been an emerging topic in recent years due to the rising need to develop virtual agents with artificial (general) intelligence. There has been much discussion on what a world model really is, how to build it, how to use it, and how to evaluate it. In this essay, starting from the imagination in the famed Sci-Fi classic Dune, and drawing inspiration from the concept of “hypothetical thinking” in psychology literature, we argue the primary goal of a world model to be {\it simulating all actionable possibilities of the real world for purposeful reasoning and acting}. We examine the key design dimensions of world modeling: data, representation, architecture, learning objective, and usage, surveying existing approaches and analyzing their tradeoffs. Building on this examination, we propose a new Generative Latent Prediction (GLP) architecture for a general-purpose world model, based on stateful, hierarchical, multi-level, and mixed continuous/discrete representations, and a generative and self-supervised learning framework, with an outlook of a Physical, Agentic, and Nested (PAN) AGI system enabled by such a model.

Submission history

From: Mingkai Deng [view email]
[v1] Mon, 7 Jul 2025 16:23:46 UTC (1,063 KB)
[v2] Fri, 18 Jul 2025 16:48:16 UTC (1,063 KB)
[v3] Sun, 27 Jul 2025 22:36:54 UTC (1,063 KB)
[v4] Tue, 16 Jun 2026 05:42:31 UTC (1,007 KB)
[v5] Wed, 17 Jun 2026 19:20:50 UTC (1,008 KB)