PulseAugur
EN
LIVE 21:29:30

New research advances robot world models for efficient planning and control · 10 sources tracked

Recent research explores advancements in world action models (WAMs) for robotics and agent planning. WAM-Cache and WAMJET focus on accelerating inference by optimizing key-value reuse and employing agentic harnesses for bottleneck identification and refinement, achieving significant speedups without compromising action quality. MobileWorldBench introduces a benchmark and dataset for semantic world modeling in GUI agents, moving beyond pixel prediction to natural language state transitions. Tempo and COSTGRAD offer new planning objectives and token selection methods for latent world models, improving efficiency and accuracy in long-horizon tasks. LeWAM and RoboJEPA explore JEPA-based architectures for robot world models, demonstrating improved alignment, planning capabilities, and scaling laws. AI

IMPACT Advances in world models and planning techniques are crucial for developing more capable and efficient AI agents in robotics and simulated environments.

RANK_REASON Multiple arXiv papers and Hugging Face daily papers detailing new research in world models for robotics and agent planning.

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 45 sources. How we write summaries →

New research advances robot world models for efficient planning and control · 10 sources tracked

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
Multiple arXiv papers and Hugging Face daily papers detailing new research in world models for robotics and agent planning.
Source corroboration
45 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
52 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [45]

  1. arXiv cs.LG TIER_1 English(EN) · Kai Ding, Yang He, Ruijie Quan, Yi Yang ·

    WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models

    arXiv:2610.11401v1 Announce Type: cross Abstract: World Action Models (WAMs) enable generalist robot manipulation by conditioning an action expert on representations from a pretrained video Diffusion Transformer (DiT). In closed-loop control, the video DiT runs at every chunk to …

  2. arXiv cs.AI TIER_1 English(EN) · Shashank Hegde, Alexander Popov, Elie Aljalbout, Nikolai Smolyanskiy ·

    LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC

    arXiv:2610.12407v1 Announce Type: cross Abstract: World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant information which can complicate downstream predictions. We introduce LeWAM, a …

  3. arXiv cs.AI TIER_1 English(EN) · Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka, Aditya Grover ·

    MobileWorldBench: Towards Semantic World Modeling For Mobile Agents

    arXiv:2512.14014v2 Announce Type: replace Abstract: World models have shown great utility in improving the task performance of embodied agents. While prior work largely focuses on pixel-space world models, these approaches face practical limitations in GUI settings, where predict…

  4. arXiv cs.LG TIER_1 English(EN) · Lama Moukheiber, Haotian Xue, Yongxin Chen ·

    How Long, Not How Close: A Learned Temporal Metric for Planning in Latent World Models

    arXiv:2610.04988v2 Announce Type: replace Abstract: Latent world models plan by rolling a frozen predictor forward under candidate action sequences and ranking the candidates by the latent distance between their imagined end state and the goal. However, this ranking breaks down w…

  5. arXiv cs.LG TIER_1 English(EN) · Yingchen Xu, Edward Grefenstette ·

    Sparse Planning in Visual World Models via Cost Gradients

    arXiv:2610.10274v1 Announce Type: new Abstract: Token-based world models enable fine-grained latent planning, but repeatedly processing large spatial token grids makes action search expensive. We introduce COSTGRAD, a training-free, goal-conditioned selector that ranks spatial to…

  6. Hugging Face Daily Papers TIER_1 English(EN) ·

    DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

    We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can impair action following, while limited coverage of…

  7. Hugging Face Daily Papers TIER_1 English(EN) ·

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

    Video generators and video-based world models can synthesize plausible visual trajectories, but long-horizon procedural tasks require generation to adapt to what has actually been produced. A model must determine the next action from its generated state, execute that action, and …

  8. Hugging Face Daily Papers TIER_1 English(EN) ·

    RoboJEPA: Scaling Robotic Latent World Models

    Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open problem that slows progress in the field…

  9. arXiv cs.AI TIER_1 English(EN) · Wanjin Feng, Baobin Zhang, Ao Yu, Shibo Feng, Xi Wang, Xingyu Gao ·

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

    arXiv:2610.08627v1 Announce Type: new Abstract: Long-horizon world-model planning typically relies on autoregressive rollouts, where predicted states are repeatedly fed back into the model. This preserves temporal structure but creates a horizon-length sequential path and exposes…

  10. arXiv cs.AI TIER_1 English(EN) · Changbai Li, Sirui Li, Yichen Yang, Tongfei Chen, Zichao Feng, Shuwei Shao, Huobin Tan ·

    How Much Planning Is Enough? Reducing Search and Computation in World-Model Planning

    arXiv:2610.08350v1 Announce Type: cross Abstract: Visual world models enable goal-directed control through decision-time action search, but their deployment efficiency is often limited by conservatively large planning budgets. We show that competitive task performance can be achi…

  11. arXiv cs.AI TIER_1 English(EN) · Le Chen, Lixin Liu, Jan Schneider, Zeju Qiu, Simon Guist, Bernhard Sch\"olkopf, Dieter B\"uchler ·

    WAMJET: A Harness for World Action Model Acceleration

    arXiv:2610.03797v2 Announce Type: replace-cross Abstract: World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction are expensive. Although existing acceleration techniques offer many wa…

  12. Hugging Face Daily Papers TIER_1 English(EN) ·

    RoboJEPA: Scaling Robotic Latent World Models

    Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open problem that slows progress in the field…

  13. Hugging Face Daily Papers TIER_1 English(EN) ·

    Long-WAM: Scaling the Context of World-Action Models

    Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system framework for scaling the context of causal world-action models under real-time control constraints. Our cent…

  14. arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Sheng-Jun Huang ·

    Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control

    World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay, packet loss, reordering, and actuator buffering. We study how asynchronous execution changes the act…

  15. Hugging Face Daily Papers TIER_1 English(EN) ·

    Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control

    World-model controllers rely on action-conditioned dynamics for prediction and planning, yet real control systems often execute commands asynchronously due to communication delay, packet loss, reordering, and actuator buffering. We study how asynchronous execution changes the act…

  16. arXiv cs.LG TIER_1 English(EN) · Tingting Du, Ziyao Wang, Guoheng Sun, Ang Li ·

    XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation

    arXiv:2610.03516v1 Announce Type: cross Abstract: World action models (WAMs) have advanced robot control by predicting how observations and actions evolve over time. Despite this progress, RGB and action based future prediction does not explicitly address the spatial understandin…

  17. arXiv cs.LG TIER_1 English(EN) · Rohun Agrawal, Nimit Kalra, Arjun Parthasarathy, Yann LeCun, Oumayma Bounou, Pavel Izmailov, Micah Goldblum ·

    Closing the Train-Test Gap in World Models for Gradient-Based Planning

    arXiv:2512.09929v2 Announce Type: replace Abstract: World models paired with model predictive control (MPC) can be trained offline on large-scale datasets of expert trajectories and enable generalization to a wide range of planning tasks at inference time. Compared to traditional…

  18. arXiv cs.AI TIER_1 English(EN) · Dhananjay Ashok, Shantanu Agarwal, Vivek Datla, Jonathan May, Alfy Samuel ·

    How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling

    arXiv:2610.02542v1 Announce Type: new Abstract: World models (WMs) simulate the transition dynamics of environments, enabling agents to plan over the consequences of their actions. In text-based environments, fine-tuning a Language Model (LM) to serve as a WM has emerged as a dom…

  19. arXiv cs.AI TIER_1 English(EN) · Samuel Barbeau, Simon Roy, Giovanni Beltrame, Christian Desrosiers, Nicolas Thome ·

    Latent Goal Prediction from Language for Model-Based Planning

    arXiv:2606.20627v2 Announce Type: replace Abstract: Joint-Embedding Predictive Architectures (JEPAs) enable agents to plan in latent space by imagining the outcomes of candidate actions, yet task specification remains a bottleneck. Visual targets provide precise local gradients b…

  20. arXiv cs.AI TIER_1 English(EN) · Xiangcheng Zhang, Runhan Huang, Yilun Du ·

    World Action Planner: Generalizable Robot Decision-Making with Action-Conditioned World Models

    arXiv:2607.27599v2 Announce Type: replace Abstract: Building generalizable robot agents for diverse applications remains a fundamental challenge. While imitation learning-based policies can perform well in familiar training environments, they often struggle to generalize to novel…

  21. arXiv cs.LG TIER_1 English(EN) · Arjun Subramanian ·

    Counterfactual Action Evaluation, Observation Bottlenecks, and Representation Geometry in Joint-Embedding Predictive World Models

    arXiv:2610.02860v1 Announce Type: new Abstract: Low latent prediction error does not establish that a world model distinguishes the consequences of its actions. We introduce an evaluation protocol that traces the same intervention through simulator state, raster observations, tar…

  22. arXiv cs.AI TIER_1 English(EN) · Fei Zhang, Zhaochong An, Duncan Frost, Yikai Wang, Pengfei Liu, Ya Zhang, Michal Drozdzal, Amir Bar ·

    World Action Modeling with Progressive Visual Planning

    arXiv:2610.02508v1 Announce Type: new Abstract: World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruction. However, existing WAMs struggle with long-hori…

  23. Hugging Face Daily Papers TIER_1 English(EN) ·

    RealtimeWAM: One-Step Asynchronous World Action Models

    World Action Models (WAMs) incorporate visual representations from video generation backbones to guide action prediction. Recent efficient WAMs adopt Mixture-of-Transformers (MoT) architectures and compute video representations once for reuse by the action expert. However, intra-…

  24. arXiv cs.LG TIER_1 English(EN) · Takumi Hara, Kanata Suzuki ·

    Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning

    arXiv:2610.01224v1 Announce Type: new Abstract: Latent world models plan by scoring candidate action sequences with distances in latent space. However, task success is judged by physical quantities, which we call the success-criterion quantities. In all four latent world models w…

  25. arXiv cs.LG TIER_1 English(EN) · Michael Hauri, Peter Buttaroni, Fabian A. Mikulasch, Friedemann Zenke ·

    Learning Commute-Time-Preserving World Models for Planning

    arXiv:2610.01373v1 Announce Type: new Abstract: World models allow agents to plan in latent space by choosing a sequence of actions that most reduces the distance to a given goal state. Thus, planning can benefit from latent representations whose distances mirror commute-times in…

  26. arXiv cs.LG TIER_1 English(EN) · Zheyuan Zhang, Suyu Ye, Nakul Agarwal, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Daniel Khashabi, Tianmin Shu, Vaishnav Tadiparthi ·

    JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts

    arXiv:2610.00722v1 Announce Type: new Abstract: World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics differ from those seen during training. We present JEPA-TTT, which adapts the lat…

  27. arXiv cs.AI TIER_1 English(EN) · Quanyi Li, Lan Feng, Haonan Zhang, Wuyang Li, Letian Wang, Alexandre Alahi, Harold Soh ·

    Grounded World Model: Latent Planning with Language Goals

    arXiv:2604.11751v2 Announce Type: replace-cross Abstract: World models such as DINO-WM and LeWM specify the goal with an image, which is difficult to obtain in advance for novel tasks. We present the Grounded World Model (GWM), a latent world model that enables zero-shot planning…

  28. Hugging Face Daily Papers TIER_1 English(EN) ·

    World Action Modeling with Progressive Visual Planning

    World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruction. However, existing WAMs struggle with long-horizon prediction, as generating dense video rollou…

  29. Hugging Face Daily Papers TIER_1 English(EN) ·

    UniWAM: Unified World-Action Model

    Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervision provides limited grounding in world dynamics. Conversely, world-action models inherit spatiotemporal priors from video generat…

  30. Hugging Face Daily Papers TIER_1 English(EN) ·

    Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models

    Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of Vision Foundation Models (VFMs) yields semantically rich representations that support diverse future scene understanding tasks. …

  31. arXiv cs.AI TIER_1 English(EN) · Ke Fang, Yupu Yao, Lu Cheng ·

    ATLAS: Aligned Transport of Latent Structure for Reliable World Model Planning

    arXiv:2609.36333v1 Announce Type: cross Abstract: Latent world models rely on representation geometry for planning, yet regularizing the latent marginal alone does not determine the state-to-state relationships used for action selection. We show that this can cause planning-relev…

  32. arXiv cs.AI TIER_1 English(EN) · Delin Zhao, Zhengrong Yue, Shaobin Zhuang, Junlin He, Xiaoyu Chen, Zikang Wang, Yuxin Liu, Limin Wang, Yali Wang ·

    Beyond a single latent space: a dual-latent world model for long-horizon planning

    arXiv:2609.37644v1 Announce Type: new Abstract: Latent world models often struggle with long-horizon planning despite accurate short-term predictions. Recursive rollouts accumulate errors, while distance concentration in high-dimensional latent spaces can weaken goal discriminati…

  33. Hugging Face Daily Papers TIER_1 English(EN) ·

    ATLAS: Aligned Transport of Latent Structure for Reliable World Model Planning

    Latent world models rely on representation geometry for planning, yet regularizing the latent marginal alone does not determine the state-to-state relationships used for action selection. We show that this can cause planning-relevant novelty structure to be weakened as representa…

  34. Hugging Face Daily Papers TIER_1 English(EN) ·

    JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts

    World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics differ from those seen during training. We present JEPA-TTT, which adapts the latent dynamics predictor of a pretrained action-co…

  35. arXiv cs.CV TIER_1 English(EN) · Ankan Deria, Komal Kumar, Hisham Cholakkal, Fahad Shahbaz Khan, Salman Khan ·

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

    arXiv:2610.12459v1 Announce Type: new Abstract: Video generators and video-based world models can synthesize plausible visual trajectories, but long-horizon procedural tasks require generation to adapt to what has actually been produced. A model must determine the next action fro…

  36. arXiv cs.CV TIER_1 English(EN) · Junyan Li, Ruizhi Li, Yu Liu, Xiangshuo Liu, Mingchao Sun, Hongyu Pan, Mu Xu, Lue Fan, Zhaoxiang Zhang ·

    DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training

    arXiv:2610.12468v1 Announce Type: cross Abstract: We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces two obstacles: imprecise calibration can …

  37. arXiv cs.CV TIER_1 English(EN) · Jiaming Zhang, Xuan Wang, Fuyao Zhang, Yang Cao, Lingjuan Lyu, Wei Yang Bryan Lim ·

    Right Screen, Wrong Transition: World Models as Verifiers for GUI Agents

    arXiv:2610.11942v1 Announce Type: new Abstract: A login screen that appears after a tap on Sign in is expected; the same screen after a tap on View order is an attack. For GUI agents, safety is therefore a property of the transition rather than of the screen, and a monitor that i…

  38. arXiv cs.CV TIER_1 English(EN) · Ziyang Ye, Junchao Huang, Evelyn Zhang, Zhihao Xie, Ruicheng Zhang, Boyao Han, Litao Ban, Ziye Wang, Xinting Hu, Shaoshuai Shi, Zhuotao Tian, Li Jiang ·

    WorldCast: Distributed Multiplayer World Models

    arXiv:2610.12412v1 Announce Type: new Abstract: Multiplayer world models must generate independently controlled views with consistent representations of both players and their shared environment. Most existing approaches coordinate multiple players through joint multi-view genera…

  39. arXiv cs.CV TIER_1 English(EN) · Boming Tan, Xiangdong Zhang, Yan Xia, Qi Zhu, Deyi Ji, Xue Yang, Shaofeng Zhang ·

    IntactWorld: Joint World Modeling with Intact Features

    arXiv:2610.11174v1 Announce Type: new Abstract: While recent video generation models synthesize highly realistic visuals, they lack a genuine understanding of intrinsic real-world logic. Existing methods attempt to understand the world by internalizing diverse world knowledge, ye…

  40. arXiv cs.CV TIER_1 English(EN) · Wei Huang, Bohan Zhang, Chenzhi Liu, Isabella Liu, Shuai Yang, Weian Mao, Luozhou Wang, Yicheng Xiao, Weifeng Lin, Qixin Hu, Bryan Chu, Sifei Liu, Linxi Fan, Xiaojuan Qi, Song Han, Yukang Chen ·

    Long-WAM: Scaling the Context of World-Action Models

    arXiv:2610.10528v1 Announce Type: cross Abstract: Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system framework for scaling the context of causal world-action mo…

  41. arXiv cs.CV TIER_1 English(EN) · Marco Giberna, Miguel Fernandez-Cortizas, Jose Luis Sanchez Lopez, Holger Voos ·

    A Review Of Robotic World Models For Dynamic Environments Based On Factor And Scene Graphs

    arXiv:2610.08800v1 Announce Type: cross Abstract: Models based on graphs have emerged in robotics as a powerful foundation for internal world representations, where factor and scene graphs are among the most prominent model types found in the related literature and in successful …

  42. arXiv cs.CV TIER_1 English(EN) · Sitian Shen, Jiuming Liu, Mengmeng Liu, Yian Wang, Michael Ying Yang, Francesco Nex, Hao Cheng, Daniele De Martini, Ayush Tewari, Per Ola Kristensson ·

    Artemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory Update

    arXiv:2610.07031v1 Announce Type: new Abstract: Recent video world models have witnessed the paradigm shift from single-agent to multi-agent involvements, which can reveal more complicated dynamics and cross-agent interaction in the real world. However, existing approaches common…

  43. arXiv cs.CV TIER_1 English(EN) · Heng Yu, David D. Yuan, Juze Zhang, Changan Chen, Yao Feng, Michelle Baldonado, Steve Cousins, Li Fei-Fei, Jiajun Wu, Ehsan Adeli ·

    OpenWAM: An Open Framework for Composable World-Action Models

    arXiv:2610.07922v1 Announce Type: cross Abstract: World-action models (WAMs) couple future prediction with robot control, yet existing systems often vary the video backbone, interaction structure, supervision, and inference procedure simultaneously, making their design choices di…

  44. arXiv cs.CV TIER_1 English(EN) · Efstathios Karypidis, Spyros Gidaris, Nikos Komodakis ·

    Latent-Foresight: End-to-End Learning Predictable Representations for Latent World Models

    arXiv:2610.01942v1 Announce Type: new Abstract: Predicting the future evolution of a scene is a fundamental capability for world modeling. Recent work has shown that operating in the feature space of Vision Foundation Models (VFMs) yields semantically rich representations that su…

  45. arXiv cs.CV TIER_1 English(EN) · Ali Alrasheed, Basim Azam, Naveed Akhtar ·

    The Planning Limits of Latent World Models

    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 existing studies mainly demonstrate what these models can accomplish, leaving unclear…