method · first seen 4 Oct 2026
world model
Also: ACWM, AC-WM, GUI world model, robot world model, multi world model, game world models, agent world model
Learned internal model of environment dynamics used by an agent to predict outcomes and plan.
A world model is a learned model of environment dynamics that lets an agent predict the consequences of actions and plan in imagination. The sources show the idea spreading into many domains: action-conditioned video generation for games and interactive scenes (Genie 4 from DeepMind, VAST-AI's EdenLive renderer, GameWM), JEPA-style latent-space planners for robot manipulation, software world models that predict downstream breakage from coding-agent edits, clinical simulators for vasopressor dosing, and a weather model that learns data assimilation end-to-end. A hobbyist post training a small model to imitate a terminal shows developer interest too. The concept itself dates back decades and is mainstream.
The current activity is less about the concept than about its spread from robotics and games into software agents, medicine and earth science, where trust and support-gating of simulated outcomes become the main open problems.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 23 on 14 Nov 2026 · 179 mentions in 28 days · 172 independent groups · papers → code → discussion · first seen 6 weeks ago · acceleration +0.01
Earliest sources
- Tackling Sim-to-Real Mismatch Through Sampling-Based Disturbance Observers: From Analytical Models to Learned World ModelsPapers · 4 Oct 2026 · Tianqi Zhu, Jun Yang, Jianliang Mao, Cong Li, Shihua Li
- PreAct-Nav: Agentic Reasoning Before Action for Urban NavigationPapers · 4 Oct 2026 · Jing Xie, Shouwei Ruan, Yubin Wang, Yuxiang Zhang, Junwei Yang, Songchang Jin, D…
- PWM: Personalized World Models with Online Reinforcement LearningPapers · 4 Oct 2026 · Zhexin Lou, Guancheng Lu, Zeyu Zhang, Yi Zhang, Yang Zhao, Hao Tang
- Software World Models: From Consequence Prediction to Decision ValuePapers · 4 Oct 2026 · Tongli Su, Yuntong Hu, Liang Zhao, Bowen Zhu, JayaSai Somasundaram, Hasibul Haqu…
- BeliefGraph-JEPA: Structured Latent World Models for Action-Conditioned Time SeriesPapers · 4 Oct 2026 · Yue Li, Kangqi Ni, Zhen Tan, Tianlong Chen
- Artemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory UpdatePapers · 4 Oct 2026 · Sitian Shen, Jiuming Liu, Mengmeng Liu, Yian Wang, Michael Ying Yang, Francesco…
Latest sources
- Lazy-MOSAIC: Accelerating Skill-Centric Manipulation Planning with Learned Skill-Effect World ModelsPapers · 16 Nov 2026 · Itamar Mishani, Mukund Krishnakumar, Oren Salzman, Maxim Likhachev
- Auditing World-Model Explanations in Retail Forecasting: Faithfulness, Accuracy and Price ResponsePapers · 16 Nov 2026 · Kathik Iyer
- XMimic and XSoma: Learning Humanoid Motion Tracking and Locomotion in Under a MinutePapers · 16 Nov 2026 · Nico Bohlinger, Jan Peters
- JEPA4R: Embodied JEPA World Models with 4D Point PlanningPapers · 15 Nov 2026 · Jiarui Dong, Zhiheng Liang, Yanjun Li, Zeyu Zhang, Heejeong Nam, Haoyu Chen, Hao…
- GameWM: Toward Next-Generation Video Games with Interaction-Centric World ModelsPapers · 14 Nov 2026 · Bing He, Runze Wang, Fei Zha, Zhongyuan Wu, Ke Xu, Tao Zhuang, Yuxuan Xie, Zhong…
- WA-JEPA: Goal-Aware Predictive Feedback Action Refinement for a World-Action ModelPapers · 14 Nov 2026 · Tao An, Weihang Liang, Tianqi Wang, Chuqing Cao, Wenming Tan, Kai Zhang, Haibo L…
- After 600 experiments, here's what I discovered about JEPA world modelsDiscussion · 13 Nov 2026 · halcdev · 295 points
- When to Trust Simulated Patient Responses:Support-Gated World Models for Vasopressor Decision SupportPapers · 13 Nov 2026 · Yifan Jin, Tao Liu
- WeatherDreamer: Learning a World Model from Multimodal Earth ObservationsPapers · 13 Nov 2026 · Kate Duffy, Elise Penn, Tristan Ballard, August Posch, Thomas J. Vandal
- Recovered or Memorized? Investigating Dynamical Consistency and Faithfulness in World Model LatentsPapers · 13 Nov 2026 · Jerome Francisco, Kyle Deng, George Flint, Kevin Zhu
- Toward Universal Translatability: On the Statistical Ontology of Generative AIPapers · 13 Nov 2026 · Katia Schwerzmann
- Beyond Prediction Gain: LASR as a Metric for Action-Grounded Latents in World ModelsPapers · 13 Nov 2026 · Yu Zhou, Changsong Lei, Yixiang Wei, Kairui Wen, Huankun Sheng, Ming Li, Yeying…