iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| 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 |