World Models As An Intermediary Between Agents And The Real World

Abstract

Large language model (LLM) agents trained using reinforcement learning has achieved superhuman performance in low-cost environments like games, mathematics, and coding. However, these successes have not translated to complex domains where the cost of interaction is high, such as the physical cost of running robots, the time cost of ML engineering, and the resource cost of scientific experiments. The true bottleneck for achieving the next level of agent performance for these complex and high-cost domains lies in the expense of executing actions to acquire reward signals. To address this gap, this paper argues that we should use world models as an intermediary between agents and the real world. We discuss how world models, viewed as models of dynamics, rewards, and task distributions, can overcome fundamental barriers of high-cost actions such as extreme off-policy learning and sample inefficiency in long-horizon tasks. Moreover, we demonstrate how world models can provide critical and r

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyang2026world

Related papers

• Mental Modeling Of Reinforcement Learning Agents By Language Models (2024)0.00
• Decentralized Transformers With Centralized Aggregation Are Sample-efficient Multi-agent World Models (2024)0.00
• Language-conditioned World Model Improves Policy Generalization By Reading Environmental Descriptions (2025)0.00
• General Agents Contain World Models (2025)0.00
• MABL: Bi-level Latent-variable World Model For Sample-efficient Multi-agent Reinforcement Learning (2023)0.00
• Reinforcement Learning With World Model (2019)0.00
• Benchmarking World-model Learning (2025)1.57
• Foundation World Models For Agents That Learn, Verify, And Adapt Reliably Beyond Static Environments (2026)0.00