iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Fang, Jianjie, Lei, Yingshan, Wan, Qin, Wang, Ziyou, Huang, Yuchao, Xu, Yongyan, Zhao, Baining, Zhang, Weichen, Gao, Chen, Chen, Xinlei, Li, Yong
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913093430280192
author Fang, Jianjie
Lei, Yingshan
Wan, Qin
Wang, Ziyou
Huang, Yuchao
Xu, Yongyan
Zhao, Baining
Zhang, Weichen
Gao, Chen
Chen, Xinlei
Li, Yong
author_facet Fang, Jianjie
Lei, Yingshan
Wan, Qin
Wang, Ziyou
Huang, Yuchao
Xu, Yongyan
Zhao, Baining
Zhang, Weichen
Gao, Chen
Chen, Xinlei
Li, Yong
contents Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, reasoning, and action. Yet current research still lacks large-scale datasets and unified benchmarks to evaluate their physical interaction capabilities. To address this, we propose iWorld-Bench, a comprehensive benchmark for training and testing world models on interaction-related abilities such as distance perception and memory. We construct a diverse dataset with 330k video clips and select 2.1k high-quality samples covering varied perspectives, weather, and scenes. As existing world models differ in interaction modalities, we introduce an Action Generation Framework to unify evaluation and design six task types, generating 4.9k test samples. These tasks jointly assess model performance across visual generation, trajectory following, and memory. Evaluating 14 representative world models, we identify key limitations and provide insights for future research. The iWorld-Bench model leaderboard is publicly available at iWorld-Bench.com.
format Preprint
id arxiv_https___arxiv_org_abs_2605_03941
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
Fang, Jianjie
Lei, Yingshan
Wan, Qin
Wang, Ziyou
Huang, Yuchao
Xu, Yongyan
Zhao, Baining
Zhang, Weichen
Gao, Chen
Chen, Xinlei
Li, Yong
Computer Vision and Pattern Recognition
Artificial Intelligence
Achieving Artificial General Intelligence (AGI) requires agents that learn and interact adaptively, with interactive world models providing scalable environments for perception, reasoning, and action. Yet current research still lacks large-scale datasets and unified benchmarks to evaluate their physical interaction capabilities. To address this, we propose iWorld-Bench, a comprehensive benchmark for training and testing world models on interaction-related abilities such as distance perception and memory. We construct a diverse dataset with 330k video clips and select 2.1k high-quality samples covering varied perspectives, weather, and scenes. As existing world models differ in interaction modalities, we introduce an Action Generation Framework to unify evaluation and design six task types, generating 4.9k test samples. These tasks jointly assess model performance across visual generation, trajectory following, and memory. Evaluating 14 representative world models, we identify key limitations and provide insights for future research. The iWorld-Bench model leaderboard is publicly available at iWorld-Bench.com.
title iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.03941