The paper introduces an action‑conditioned world‑modeling framework that turns Earth‑system simulator trajectories into training data for controllable state‑transition learning. By pretraining on naturally observed state changes as implicit action supervision and using masked response learning, the model can infer unobserved variables and learn coupled system dependencies. Experiments on ecosystem dynamics across six global regions demonstrate that the model maintains long‑horizon emulation accuracy while enabling structural interventions and coherent responses in coupled ecosystem‑cycle variables.
By Zhihao Wang, Ruichen Wang, Ruohan Li, Lei Ma, George Hurtt, Xiaowei Jia, Gengchen Mai, Shaowen Wang, Yiqun Xie
arXiv:2610.42096v1 Announce Type: cross
Abstract: World action models (WAMs) learn latent variables from observations and use these to both predict the evolution of the scene and to generate actions....
By Juntao Cheng, Jinzhou Tang, Fan Feng, Henrik I. Christensen, Yujia Zheng
The paper formalizes controllable user simulation as a causal inference problem, showing that standard supervised fine‑tuning on post‑hoc trajectory labels introduces a look‑ahead bias that breaks causal consistency. This bias leads to a phenomenon called controllability collapse, where evaluation metric variance explodes under policy shift. The authors propose theoretical conditions for accurate simulation and practical training mitigations—such as a priori controls, step‑wise dynamic controls, and direct policy‑conditioned learning—to eliminate look‑ahead bias, preserve natural variance, and achieve robust zero‑shot generalization to unseen agent behaviors.
By Guy Tennenholtz, Ofer Meshi, Amir Globerson, Uri Shalit, Jihwan Jeong, Craig Boutilier
TabCausal is a causal discovery foundation model that learns to map datasets directly to causal graphs by pretraining across diverse causal environments. It uses a dynamic task construction strategy to expose the model to varied graph priors, mechanisms, noise models, dimensions, sample sizes, and intervention regimes, improving transferability from observational and mixed‑interventional data. On large synthetic benchmarks and a new protocol‑guided semantic benchmark, TabCausal outperforms many classical baselines and shows robust structure recovery, especially when interventional evidence is available.
By Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, Han-Jia Ye
arXiv:2607. 27973v1 Announce Type: new Abstract: Recently, Reinforcement Learning (RL) has emerged as a crucial paradigm for the post-training of Large Language Model (LLM) agents.
By Cong Li, Peixi Peng, Yisen Zhao, Xinyu Hu, Shudong Liu, Zhan Su, Zhuojian Li
The paper introduces AnyGoal, a benchmark that tests world models on goal‑shifted task variants where state and action factors are recombined beyond the combinations seen in expert rollouts. It evaluates how well different world‑model families generalize to these unseen recombinations across multiple environments, revealing consistent failures. The study analyzes dynamics and representation shortcomings to identify where current models succeed and where they struggle in goal‑shifted prediction and planning.
By Heejeong Nam, Divyat Mahajan, Quentin Le Lidec, Randall Balestriero, David Klindt
arXiv:2606. 25527v1 Announce Type: new Abstract: Online reinforcement learning (RL) agents increasingly depend on knowledge acquired offline to achieve practical efficiency.
By Guozheng Ma, Lu Li, Zilin Wang, Pierre-Luc Bacon, Dacheng Tao
The paper introduces Retrospective World Modeling, a new paradigm for vision‑language‑model (VLM) agents that allows them to reason backward by estimating which action most likely caused a state transition. It proposes the Self‑Consistency Reward (SCR), an intrinsic signal that measures how well a policy action aligns with this retrospective explanation, providing dense transition‑level feedback. Experiments demonstrate that incorporating SCR improves policy robustness and generalization compared to purely prospective world‑modeling approaches.
By Yongjiang Liu, Jie Zhang, Haoyue Zhang, Jingcai Guo, Deze Zeng, Song Guo
arXiv:2607. 18715v1 Announce Type: new Abstract: Latent world models underpin much of modern model-based control, yet current action-conditioned formulations supervise the next-latent transition with a single, undifferentiated target, forcing a monolithic learning signal to absorb every source of state change.
By Yi-Ge Zhang, Tianqi Du, Qi Zhang, Yisen Wang
arXiv:2609.38334v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-mode...
By Yuhan Guo, Jinming Liu, Liang Xu, Ziqiang Li, Jianguo Huang, Zhicheng Wang, Hu Zhu, Qiuyu Chen, Yuntao Wei, Xin Jin, Wenjun Zeng
The paper introduces OneWM, a unified causal training framework that treats actions as both conditions for world prediction and targets for policy learning within a shared video-action architecture. Experiments on LIBERO, LIBERO-Plus, and RoboCasa365 show that learning forward dynamics conditioned on specified actions improves policy performance and generalization, while action learning enhances multi‑view world‑prediction fidelity. These findings demonstrate reciprocal benefits between world modeling and action generation under unified causal training.
By Yue Su, Bokai Lin, Xinkai Wang, Chubin Zhang, Xiangnan Wu, Kuan Zhang, Weiyang Jin, Jiwen Yu, Yiming Li, Cewu Lu, Lixin Yang, Xihui Liu
arXiv:2608.30897v1 Announce Type: new
Abstract: World models are becoming core infrastructure for embodied intelligence, with action-conditioned video generation providing controllable predictions of...
By Jianjie Fang, Xvyuan Liu, Ziyou Wang, Rongze Tang, Zhaolu Wang, Zhuohang Li, Xin Zhang, Haisheng Su, Chen Gao, Wei Wu, Xinlei Chen, Yong Li