Modern generative world models render increasingly realistic action-controllable futures, yet they frequently hallucinate: rollouts remain visually fluent while drifting from the ground-truth dynamics. We hypothesize that hallucination concentrates in low-coverage regions of the state-action space, where lightweight data-centric signals can both detect it and guide mitigation.
WorldAgen is a unified framework that jointly learns world modeling and action prediction using a shared Transformer backbone with two specialized heads. It introduces a Mixed Unidirectional Attention Mask to separate the world model and agent model, and enables Test-Time Training (TTT) by sampling exploratory actions and updating the world model with real state transitions. Experiments on CALVIN and LIBERO show that WorldAgen matches or surpasses state‑of‑the‑art methods, especially when TTT is applied to a few samples.
By Chi Wan, Kangrui Wang, Yuan Si, Pingyue Zhang, Manling Li
World-Coherent Decoding (WCD) is a test-time planning framework for World Action Models (WAMs) that treats rollouts as falsifiable future–action hypotheses. At each decision step, WCD samples multiple candidates from a frozen WAM and ranks them using flow-based video surprisal for visual plausibility and action path effort for generation stability. After execution, the observed outcome audits the chosen imagination, producing a mismatch signal that trains a lightweight online predictor to improve future candidate selection, thereby enhancing reliability without updating the backbone model.
By Chuhan Zhang, Seiji Ito, Kenta Hoshino, Satoshi Ikehata, Ikuro Sato
arXiv:2609.39235v1 Announce Type: cross
Abstract: World models offer a promising way to help robots understand how the physical world evolves and plan complex behaviours through imagination. Yet exis...
By Ali Alrasheed, Basim Azam, Naveed Akhtar
arXiv:2608. 11605v1 Announce Type: new Abstract: World Action Models (WAMs) couple future visual prediction with robot action generation, enabling policies to model how the physical world evolves during interaction.
By Jiakai Huang, Zhongbo Wu, Zheng Zhang, Zihan Wang, Shan You, Tao Huang
arXiv:2607. 14180v1 Announce Type: cross Abstract: World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset.
By Logan Mondal Bhamidipaty, Mykel Kochenderfer, Subramanian Ramamoorthy