World models: Enabling the next AI revolution

What distinguishes a cat that climbs a cabinet and turns a doorknob to exit a room from your favorite large language model (LLM) chatbot or agent?The cat possesses an intuitive understanding of physical laws-gravity, friction, its own body dynamics-and can plan and execute a sequence of actions without explicit instruction or prior training on that specific task.In contrast, an LLM chatbot generates responses token by token, trained on vast symbolic datasets but lacking three abilities: (1) an understanding of the physical world, (2) an ability to predict the consequences of its own actions, (3) an ability to plan a sequence of actions to accomplish a particular task.Future advanced machine intelligence must integrate the cat's embodied reasoning capabilities alongside the linguistic proficiency of current models.This paper argues that scaling token-generative architectures alone will not deliver the next AI revolution.Instead, progress requires a fundamental shift toward world models: Learned internal representations that encode the state of the environment, predict the outcomes of potential actions, and enable planning under explicit objectives and constraints.Contemporary AI systems remain surprisingly limited in the kinds of intelligence that humans and animals demonstrate effortlessly in physical settings (LeCun, 2022).Moreover, this worldmodel paradigm must extend to human-facing agents that comprehend users' knowledge, beliefs, goals, and social contexts (Fung et al., 2025).

Authors

Publication Details

Journal
AI Magazine
Published
2026-11-13
DOI
https://doi.org/10.1002/aaai.70110
Primary Topic
AI-based Problem Solving and Planning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

World models: Enabling the next AI revolution

Yann LeCun, Pascale Fung
AI Magazine
AI-based Problem Solving and Planning
article

World models: Enabling the next AI revolution

Yann LeCun, Pascale Fung
article en

Abstract

What distinguishes a cat that climbs a cabinet and turns a doorknob to exit a room from your favorite large language model (LLM) chatbot or agent?The cat possesses an intuitive understanding of physical laws-gravity, friction, its own body dynamics-and can plan and execute a sequence of actions without explicit instruction or prior training on that specific task.In contrast, an LLM chatbot generates responses token by token, trained on vast symbolic datasets but lacking three abilities: (1) an understanding of the physical world, (2) an ability to predict the consequences of its own actions, (3) an ability to plan a sequence of actions to accomplish a particular task.Future advanced machine intelligence must integrate the cat's embodied reasoning capabilities alongside the linguistic proficiency of current models.This paper argues that scaling token-generative architectures alone will not deliver the next AI revolution.Instead, progress requires a fundamental shift toward world models: Learned internal representations that encode the state of the environment, predict the outcomes of potential actions, and enable planning under explicit objectives and constraints.Contemporary AI systems remain surprisingly limited in the kinds of intelligence that humans and animals demonstrate effortlessly in physical settings (LeCun, 2022).Moreover, this worldmodel paradigm must extend to human-facing agents that comprehend users' knowledge, beliefs, goals, and social contexts (Fung et al., 2025).

AI MagazineVol. 47(4)
AI-based Problem Solving and Planning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon