# Scaling Laws for Pre-training Agents and World Models

arXiv: https://arxiv.org/abs/2411.04434 · HTML: https://mlsanity.com/paper/2411.04434/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 40 of its 47 references that are in the map.
- First posted on arXiv 7 Nov 2024.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 30 of 40)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [Deep Learning Scaling is Predictable, Empirically](https://mlsanity.com/paper/1712.00409/) (2017)
- [Scaling Laws for Autoregressive Generative Modeling](https://mlsanity.com/paper/2010.14701/) (2020)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [Scaling Data-Constrained Language Models](https://mlsanity.com/paper/2305.16264/) (2023)
- [Explaining Neural Scaling Laws](https://mlsanity.com/paper/2102.06701/) (2021)
- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022)
- [A Constructive Prediction of the Generalization Error Across Scales](https://mlsanity.com/paper/1909.12673/) (2019)
- [Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations](https://mlsanity.com/paper/2405.18392/) (2024)
- [Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws](https://mlsanity.com/paper/2401.00448/) (2023)
- [A Solvable Model of Neural Scaling Laws](https://mlsanity.com/paper/2210.16859/) (2022)

## Built on by (most cited first, 23 of 23)

- [AdaWorld: Learning Adaptable World Models with Latent Actions](https://mlsanity.com/paper/2503.18938/) (2025)
- [Scaling Laws for Optimal Data Mixtures](https://mlsanity.com/paper/2507.09404/) (2025)
- [Scaling Laws for Native Multimodal Models](https://mlsanity.com/paper/2504.07951/) (2025)
- [SIMA 2: A Generalist Embodied Agent for Virtual Worlds](https://mlsanity.com/paper/2512.04797/) (2025)
- [How Much is Enough? The Diminishing Returns of Tokenization Training Data](https://mlsanity.com/paper/2502.20273/) (2025)
- [Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing](https://mlsanity.com/paper/2601.04575/) (2026)
- [Fast Autoregressive Video Generation with Diagonal Decoding](https://mlsanity.com/paper/2503.14070/) (2025)
- [Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval](https://mlsanity.com/paper/2602.19961/) (2026)
- [MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?](https://mlsanity.com/paper/2502.09933/) (2025)
- [Curious Causality-Seeking Agents Learn Meta Causal World](https://mlsanity.com/paper/2506.23068/) (2025)
- [Pixels to Play: A Foundation Model for 3D Gameplay](https://mlsanity.com/paper/2508.14295/) (2025)
- [Generative Modeling of Individual Behavior at Scale](https://mlsanity.com/paper/2502.14998/) (2025)
- [Evaluating the Robustness of Chinchilla Compute-Optimal Scaling](https://mlsanity.com/paper/2509.23963/) (2025)
- [Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data](https://mlsanity.com/paper/2502.19544/) (2025)
- [Adapting Vision-Language Models for Evaluating World Models](https://mlsanity.com/paper/2506.17967/) (2025)
- [Learning to play: A Multimodal Agent for 3D Game-Play](https://mlsanity.com/paper/2510.16774/) (2025)
- [Jasmine: A Simple, Performant and Scalable JAX-based World Modeling Codebase](https://mlsanity.com/paper/2510.27002/) (2025)
- [Teach and Grow: An Agent-Centered Architecture for General Robot Learning](https://mlsanity.com/paper/2608.17209/) (2026)
- [On Training in Imagination](https://mlsanity.com/paper/2605.06732/) (2026)
- [Practical Scaling Laws: Converting Compute into Performance in a Data-Constrained World](https://mlsanity.com/paper/2605.09189/) (2026)
- [WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning](https://mlsanity.com/paper/2608.22591/) (2026)
- [How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models](https://mlsanity.com/paper/2608.28404/) (2026)
- [RoboJEPA: Scaling Robotic Latent World Models](https://mlsanity.com/paper/2610.10515/) (2026)

## Abstract (arXiv)

The performance of embodied agents has been shown to improve by increasing model parameters, dataset size, and compute. This has been demonstrated in domains from robotics to video games, when generative learning objectives on offline datasets (pre-training) are used to model an agent's behavior (imitation learning) or their environment (world modeling). This paper characterizes the role of scale in these tasks more precisely. Going beyond the simple intuition that `bigger is better', we show that the same types of power laws found in language modeling also arise in world modeling and imitation learning (e.g. between loss and optimal model size). However, the coefficients of these laws are heavily influenced by the tokenizer, task & architecture -- this has important implications on the optimal sizing of models and data.