General Agents Contain World Models

Abstract

Are world models a necessary ingredient for flexible, goal-directed behaviour, or is model-free learning sufficient? We provide a formal answer to this question, showing that any agent capable of generalizing to multi-step goal-directed tasks must have learned a predictive model of its environment. We show that this model can be extracted from the agent's policy, and that increasing the agents performance or the complexity of the goals it can achieve requires learning increasingly accurate world models. This has a number of consequences: from developing safe and general agents, to bounding agent capabilities in complex environments, and providing new algorithms for eliciting world models from agents.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrichens2025general

Related papers

• Language-conditioned World Model Improves Policy Generalization By Reading Environmental Descriptions (2025)0.00
• Foundation World Models For Agents That Learn, Verify, And Adapt Reliably Beyond Static Environments (2026)0.00
• World Models As An Intermediary Between Agents And The Real World (2026)0.00
• Decentralized Transformers With Centralized Aggregation Are Sample-efficient Multi-agent World Models (2024)0.00
• Open-ended Learning Leads To Generally Capable Agents (2021)0.00
• Learning To Predict Without Looking Ahead: World Models Without Forward Prediction (2019)0.00
• Recurrent World Models Facilitate Policy Evolution (2018)0.00
• Benchmarking World-model Learning (2025)1.57