World Models

Follow this topic Ask about this topic

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

366 papers72 papers in the last four weeks, up 71% on the four weeks before. 0.4% of all new papers.

Bayesian Offline Multi-Agent Reinforcement Learning with Latent World Models
Oct 29, 2026Xi Xiong, Lu Liu, Yiming Li +1Offline MARL Model-Based RL
British Open-ended Learning and Discovery Lab (BOLD) · Tongji University · University of Oxford
CAD-WAM: Anticipating Geometry for Text-to-CAD Generation
Oct 29, 2026Zhengyang Li, Weijie Zheng, Yuxin Cui +3Text-to-CAD Generation Parametric CAD Modeling
University of Science and Technology of China · Nanyang Technological University
Context Compaction for World Models
Oct 28, 2026Hayder TirmaziWorld Models LLM World Models
1Boston University, Boston, Massachusetts, USA · 2AllSpice Inc., Boston, Massachusetts, USA.
Understanding the limits of latent world models
Oct 27, 2026Rodrigo Gonzalez Laiz, Steffen SchneiderWorld Models Latent World Models
Helmholtz Munich Munich Center for Machine Learning (MCML)
RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions
Oct 27, 2026Haoyu Zhao, Yinzhou Tang, Zixuan Wang +11Embodied World Models World Models
DAMO Academy, Alibaba Group · Hong Kong Embodied AI Lab · CUHK +1
BoxWorld: Let World Engines Control and Video Generators Render
Oct 26, 2026Zike Wu, Ahmed Hatem, Chintan Trivedi +4Real-Time Interactive Video Generation Interactive World Models
University of British Columbia · Vector Institute for AI · Huawei Canada +1
Does LeWorldModel Preserve Local Action Geometry?
Oct 22, 2026Vasil Vasilev, Siddharth NayakWorld Models World Model Evaluation
Technological School Electronic Systems (TUES) · Massachusetts Institute of Technology
An Introduction to World Models for Generalist Agents
Oct 22, 2026Zhihui ZhuWorld Models World Model Learning
Department of Computer Science and Engineering The Ohio State University
From Single-Actor Environments to Multi-Actor Event Worlds: Can LLMs Be Event World Models?
Oct 21, 2026Juntong Ni, Zewen Liu, Bohan Wang +2LLM World Models World Models
Emory University
PhysiCalWorld: In-Context Physics Calibration for World Models
Oct 21, 2026Yunhao Luo, Wentao He, Yinpei Dai +5World Models Action-Conditioned World Models
University of Michigan
Exploring Temporal Context-Aware Physical Grounding in Latent World Models
Oct 20, 2026Yilei Man, Yang Chen, Jingcai GuoWorld Models Latent World Models
Department of Computing, The Hong Kong Polytechnic University · Department of Land Surveying and Geospatial Science, The Hong Kong Polytechnic University
AnyGoal: On World Model Generalization Beyond Expert Rollouts
Oct 19, 2026Heejeong Nam, Divyat Mahajan, Quentin Le Lidec +2World Models World Model-Based Planning
Brown University · Cold Spring Harbor Laboratory · Mila, Universit´e de Montr´eal +1
State World Models: Execute the Rules, Generate the Pixels
Oct 19, 2026Chan Yan Ki, Yanran Zhang, Wenzhao Zheng +5World Models Action-Conditioned World Models
Department of Automation, Tsinghua University, China · GigaAI
PrismWAM: Decoupling State Representations in World Action Models
Oct 19, 2026Tianyu Xin, Wanqi Zhong, Bowen Hu +8World Models for Robotics World Models
Tsinghua University · NVIDIA
Learning Goal-Conditioned Subgoals through Frozen Hierarchical World Models
Oct 19, 2026Xiang Kaibo, Liu QingfengHierarchical World Models World Model-Based Planning
Department of Industrial and Systems Engineering, Hosei University
ActionRoPE: Action as Coordinates for Spatially Consistent Control in Planar-Camera Game World Models
Oct 19, 2026Zhiyang Deng, Yuzhe Wu, Zijun Lin +1Action-Conditioned Video Generation World Models
Tencent · National University of Singapore · Nanyang Technological University
World Model Interpretability: From Decoding Representations to Understanding Latent Worlds
Oct 18, 2026Jize Wang, Yongcheng Jing, Xinyi Le +3World Models Latent World Models
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University · College of Computing and Data Science, Nanyang Technological University
Axiomatic World Modeling for Physics Reasoning
Oct 17, 2026Xinye Yang, Zhenyang Liu, Yuxuan Wang +1Physical Reasoning Scientific Reasoning in Language Models
Northwestern University, Evanston, IL · Department of Physics, University of Florida, Gainesville, FL · Computer & Information Science and Engineering, University of Florida, Gainesville, FL
GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations
Oct 15, 2026Nicholas Saban, Charvi Bannur, Mariya Vasileva +1World Model Evaluation LLM World Models
Patronus AI
MAIA: Anticipating Interaction Anomalies in Contact-Rich Manipulation via Multimodal World Models
Oct 15, 2026Yi Qiao, Maolin Zheng, Haoran Sun +2Anomaly Detection Contact-Rich Robotic Manipulation
School of Artificial Intelligence, Shanghai Jiao Tong University
Mallea: Building, Steering, and Memorizing Worlds with Coding Agent
Oct 15, 2026Xuanyi Liu, Ruiqi Li, Siwei MaCode World Models World Models
WorldCast: Exploring Intelligent Visual Generation in World State Prediction
Oct 14, 2026Wenhao Yan, Haodong Li, Xiaotong Li +9World Models Multimodal Generation
THU · CUHK · Meituan LongCat +4
GeoThinker- $F$ : Endogenous Predictive World Representations for Fast Spatial Intelligence
Oct 14, 2026Haoyuan Li, Qihang Cao, Huanyuan Zhou +103D VLMs 3D Spatial Reasoning
Shenzhen campus of Sun Yat-sen University · Nanyang Technological University · XPeng Motors +1
Neurosymbolic Learning of Interpretable World Models
Oct 14, 2026Riccardo Andreoni, Massimiliano Ronzani, Chiara Ghidini +2Temporal Logic World Model Learning
Fondazione Bruno Kessler · Free University of Bozen-Bolzano · Vrije Universiteit Amsterdam
Model What Matters: Decision-Guided Selective World Modeling for Language Agents
Oct 14, 2026Maolin Ran, Minda Chen, Di Huang +3World Models RL for LLM Agents
Shanghai Jiao Tong University · LongShine AI Research
SonoWorld: Towards Interactive Pose-Controllable Ultrasound World Models
Oct 14, 2026Zefan Yang, Zheyuan Zhang, Boris Maihe +7World Models Action-Conditioned World Models
United Imaging Intelligence, Boston, MA, USA · Rensselaer Polytechnic Institute, Troy, NY, USA
Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors
Oct 13, 2026Henry Che, Xuanchi Ren, Sanja Fidler +3World Models World Model Learning
NVIDIA · University of Illinois, Urbana-Champaign · University of Toronto
LongForcing: Scaling Temporal Manifold Matching for Long-Horizon World Rollout
Oct 13, 2026Ziyu Zhu, Zhaoxu Sun, Fan Jiang +5Long-Horizon Video Generation Video Diffusion Models
AMAP, Alibaba Group · Tsinghua University
SkipWorld: Latent Skip Planning with Distilled World Models for Efficient Visual Navigation
Oct 13, 2026Yifei Yang, Zehua Fan, Zike Yan +2Visual Navigation World Model-Based Planning
Institute for AI Industry Research (AIR), Tsinghua University · Hong Kong Embodied AI Lab · The Chinese University of Hong Kong +1
Multics: Generative Multi-Player World Model with Hierarchical Communication
Oct 12, 2026Kaiyi Huang, Wangbo Yu, Yukun Huang +6Interactive World Models World Models
The University of Hong Kong · ARC Lab, Tencent IEG

Oct 29, 2026J/K move · Enter open · S save

Bayesian Offline Multi-Agent Reinforcement Learning with Latent World Models

Xi Xiong, Lu Liu, Yiming Li, Jakob Foerster

British Open-ended Learning and Discovery Lab (BOLD) · Tongji University · University of Oxford

Offline MARL Model-Based RL Partially Observable RL World Models Bayesian RL

Open paper AskPDF arXiv

Model-based offline multi-agent reinforcement learning (MARL) provides a promising approach to multi-agent decision-making under partial observability, where the global state is unavailable from offline data. However, limited dataset coverage can lead to substantial out-of-distribution (OOD) model errors, which may mislead policy optimization and degrade downstream performance. Existing model-based offline MARL methods typically rely on access to global states or mitigate model errors through pessimistic or conservative policy optimization, leaving the reliability and refinement of learned world models less explored. We propose a Bayesian offline MARL framework that infers latent global states from decentralized observation-action histories and iteratively refines a posterior world model using only offline data. Building on posterior information loss, we extend this criterion to the multi-agent setting as multi-agent posterior information loss (MPIL), which provides a reliability measure for world model refinement and offline evaluation. Theoretically, we establish an upper bound on policy regret that is monotonic in MPIL and further characterize its dependence on the size and state-joint-action coverage of the offline dataset. Experiments on partially observable multi-agent variants of D4RL MuJoCo tasks demonstrate competitive policy performance across diverse offline data conditions, while MPIL-guided refinement improves world model prediction and downstream policy performance. These results support a principled connection between world model reliability, offline data coverage, and policy performance in partially observable offline MARL.