Overview

World models learn or encode how states, objects, and events evolve, often predicting what will happen under different actions or observations. These predictions can help agents plan ahead, learn with fewer real-world trials, test decisions safely, and reason about situations they cannot currently observe. Approaches range from latent-state predictors and action-conditioned video generators to object- or graph-based models, executable programs, and physics-informed dynamics. A central challenge is making predictions useful and reliable over long horizons: visual plausibility and one-step accuracy do not guarantee correct causal dynamics, persistent memory, or better decisions.

Latest papers

CardsList

398 papers38 papers in the last four weeks, down 51% on the four weeks before. 0.3% of all new papers.

  1. Latent World Action Model for GUI Agents

    Oct 9, 2026Seungjun Yu, Hojun Choi, Seojeong Park +2World ModelsAction-Conditioned World Models

  2. Visualizing the World Model in an Agent's Value Function

    Oct 9, 2026Shawheen Naderi, Fatemeh Akherati, Yubei ChenWorld ModelsInterpretability in RL

  3. JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models

    Oct 9, 2026Mengdi Liu, Chenghao Jia, Hong Chang +3Autonomous Research AgentsSelf-Evolving Agents

  4. RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions

    Oct 9, 2026Boyuan Xiao, Pu Wang, Ji Feng +1World ModelsLLM World Models

  5. EvoBelief: Falsifiable World Models for Self-Improving LLM Agents

    Oct 8, 2026Janet Wang, Jiang Guo, Yi Xiang +6World ModelsBelief Updating in LLMs

  6. What 30,000 Hours of Ego-centric Video Does Not Teach

    Oct 8, 2026Jiahua Dong, Anurag Bagchi, Yash Jangir +7Video World ModelsWorld Models

  7. WorldGuide: Goal-Directed Video World Model for Procedural Task Execution

    Oct 8, 2026Ankan Deria, Komal Kumar, Hisham Cholakkal +2Video GenerationAgentic Video Generation

  8. WorldCast: Distributed Multiplayer World Models

    Oct 8, 2026Ziyang Ye, Junchao Huang, Evelyn Zhang +9World ModelsInteractive World Models

  9. AtomWorld-Mirror: Macro-Step World Modeling of Critical Evolution Backbones for Materials Dynamics

    Oct 8, 2026Ziming Pan, Ruge Zhang, Haozhi Han +7Physics-Based SimulationComputational Materials Science

  10. RoboJEPA: Scaling Robotic Latent World Models

    Oct 7, 2026Artem Zholus, Nicolas Beltran-Velez, Jianhao Yuan +9World ModelsLatent World Models

  11. STRIKE: Learning Visual State Transitions for Physical World Modeling

    Oct 7, 2026Wenbin Teng, Tianshuo Xu, Depu Meng +5World ModelsVideo World Models

  12. Event-Aligned Visual Action Reasoning for World Action Models

    Oct 7, 2026Xiaomeng Yang, Yushu Wu, Yi Gao +4World Action ModelsWorld Models

  13. LeCuration: A Tiny World Model as a Data Curation Multi-Tool

    Oct 7, 2026Mayank Sengupta, Nirmit Desai, Eric Song +1Training Data CurationWorld Models

  14. Parallel Predictive World Models for Accurate and Efficient Long-Horizon Planning

    Oct 6, 2026Wanjin Feng, Baobin Zhang, Ao Yu +3World ModelsWorld Model-Based Planning

  15. H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning

    Oct 5, 2026Wancong Zhang, Basile Terver, Michael Rabbat +2World Models for RoboticsWorld Models

  16. Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent Training

    Oct 5, 2026Yongxin Ning, Runliang Niu, Qianli Xing +4World ModelsSynthetic Data Generation

  17. Identifiable World Models from Pretrained Diffusion Representations

    Oct 4, 2026Ruchi Sandilya, Conor Liston, Logan GrosenickLatent Dynamics ModelingWorld Models

  18. PWM: Personalized World Models with Online Reinforcement Learning

    Oct 4, 2026Zhexin Lou, Guancheng Lu, Zeyu Zhang +3World ModelsAction-Conditioned World Models

  19. Flow Policies as Actions of Skill-Level World Models: Learned and Symbolic Abstractions for Long-Horizon Planning

    Oct 3, 2026Andreu Matoses Gimenez, Andrei-Carlo Papuc, Chris Pek +1World Model-Based PlanningRobot Skill Learning

  20. DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents

    Oct 3, 2026Qinghua Xu, Guancheng Wang, Boxi Yu +2Automated Software TestingNeural Surrogate Modeling

  21. EVEWorld: Physical Evolution Supervision for Embodied World Models

    Oct 2, 2026Kaiqi Wang, Songxin Zhang, Zejian Xie +7Embodied World ModelsWorld Models

  22. DeltaWorld: Physically Consistent Interactive World Simulators via Action-Conditioned Latent Increment Learning

    Oct 2, 2026Boyuan Hou, Xiaoge Cao, Chaofan Zhang +2Action-Conditioned World ModelsInteractive World Models

  23. Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory

    Oct 1, 2026Ying Yang, Guiyu Zhang, Lianghua Huang +5Memory-Augmented Video GenerationWorld Models

  24. On the Divergence of Accuracy and Mechanism Consistency in Time Series World Models

    Oct 1, 2026Haochen Zhang, Jiaheng Guo, Zhen Xu +4World ModelsTime Series Forecasting

  25. Completion Aware Guidance for World Action Models

    Oct 1, 2026Seungyeon Kim, Junhoo Lee, Baekseung Kim +2World ModelsAction-Conditioned World Models

  26. Calibration-risk routing for controlled world-model adaptation

    Oct 1, 2026Yifan Zhang, Liang Zheng, Qifan ZhangWorld Models for RoboticsWorld Models