中文

WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform

机器人学 2026-05-19 v1 计算机视觉与模式识别

摘要

World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about environmental dynamics. However, existing embodied world model benchmarks are still largely confined to vision-only prediction, offline embodied applications, and simulator-based evaluation, making them insufficient for assessing increasingly comprehensive world models. In this work, we introduce WorldArena 2.0, an expanded benchmark that systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform. Along the modality dimension, WorldArena 2.0 extends evaluation from vision-only to visuotactile modalities, enabling assessment of multimodal perception and prediction. Along the functionality dimension, it extends beyond policy evaluation and planning to assess world models as interactive RL environments for policy optimization. Along the platform dimension, it moves beyond simulator-only evaluation to a diverse suite of simulated and real-world robotic settings across multiple embodiments. Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance, providing a comprehensive testbed for tracking progress toward embodied world models. The benchmark is available at: https://world-arena.ai.

关键词

引用

@article{arxiv.2605.17912,
  title  = {WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform},
  author = {Yu Shang and Yinzhou Tang and Yiding Ma and Zhuohang Li and Lei Jin and Weikang Su and Xin Jin and Zhaolu Wang and Ziyou Wang and Xin Zhang and Haisheng Su and Weizhen He and Wei Wu and Haoyi Duan and Gordon Wetzstein and Xihui Liu and Dhruv Shah and Zhaoxiang Zhang and Zhibo Chen and Jun Zhu and Yonghong Tian and Tat-Seng Chua and Wenwu Zhu and Chen Gao and Yong Li},
  journal= {arXiv preprint arXiv:2605.17912},
  year   = {2026}
}