What Matters in Designing World Action Models: An Empirical Study

2026-09-20

AI Summary

本文通过控制实验研究了世界动作模型的设计选择，包括因果结构、潜在空间及训练目标的影响，以指导未来系统设计。

Abstract

World Action Models (WAMs) have emerged as a promising paradigm for generalizable robot control. Despite the growing number of WAM systems, existing works often introduce unified systems that bundle together multiple design choices, such as architecture and training strategy, making it difficult to isolate individual contributions and systematically compare alternative designs. In this work, we present a controlled study that disentangles these design choices and analyzes not only their empirical effects, but also how and why they shape WAMs. More specifically, we focus on three fundamental questions in building WAMs: (1) what causal structure should govern the interaction between world modeling and action generation? (2) in which latent space should world modeling be performed? and (3) how do different world-action modeling objectives affect model behavior and performance? Through structurally controlled experiments on three representative benchmarks, RoboCasa-GR1, LIBERO, and LIBERO-Plus, we systematically compare six causal structures, eight latent representations, and four training objectives, covering popular design choices in existing WAMs. We further validate our key findings on real-robot data from the DROID dataset. We hope to provide a systematic understanding of how core design choices affect world-action modeling and what principles can guide the development of future WAM systems.

Problem

• World Action Models
• design choices
• causal structure
• latent space
• modeling objectives

Innovation

• causal structure
• latent space
• training objectives