Overview

World Model Evaluation studies whether a model captures how an environment changes, especially when an agent acts or observations are missing. Approaches include open-loop prediction metrics, action-conditioned rollouts, closed-loop policy tests, physics-grounded diagnostics, and human or vision-language model judging. Benchmarks span robotic manipulation such as LIBERO and RoboTwin, driving such as NuPlan, and interactive GUI, web, and game environments. A central challenge is that visual realism and one-step accuracy often fail to predict physical consistency, long-term reliability, or planning success, so evaluation remains fragmented across tasks and horizons.

Latest papers

CardsList

245 papers40 papers in the last four weeks, down 25% on the four weeks before. 0.3% of all new papers.

  1. WebWorld: A Large-Scale World Model for Web Agent Training

    Feb 16, 2026Zikai Xiao, Jianhong Tu, Chuhang Zou +7LLM World ModelsWorld Model Learning

  2. OccStress: Stress-Testing the 4D Occupancy Forecasting Chain

    Dec 17, 2025Yu Zheng, Jie Hu, Jiaqi Xiong +4Forecasting Benchmarks3D Occupancy Prediction

  3. MobileWorldBench: Towards Semantic World Modeling For Mobile Agents

    Dec 16, 2025Shufan Li, Konstantinos Kallidromitis, Akash Gokul +3World ModelsMobile GUI Agents

  4. OmniNWM: Omniscient Driving Navigation World Models

    Oct 21, 2025Bohan Li, Zhuang Ma, Dalong Du +10Action-Conditioned Video GenerationWorld Model Learning

  5. A Comprehensive Survey on World Models for Embodied AI

    Oct 19, 2025Xinqing Li, Xin He, Le Zhang +3World Model LearningWorld Models for Robotics