Motus2: A Self-Evolving General World Model for Dexterous Manipulation

• URL: http://arxiv.org/abs/2608.30237v1
• Date: Mon, 31 Aug 2026 04:44:33 GMT
• Title: Motus2: A Self-Evolving General World Model for Dexterous Manipulation
• Abstract summary: General embodied agents should perceive, predict, act, evaluate, and improve within a unified system.<n>We present Motus2, a self-evolving general world model for dexterous manipulation.
• Score: 44.91498765476382
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: General embodied agents should perceive, predict, act, evaluate, and improve within a unified system. World models have shown great promise in building such agents, yet existing models typically append an action output head to a world simulator, without coupling them into a closed decision-and-learning loop for policy improvement. We present Motus2, a self-evolving general world model for dexterous manipulation. Motus2 advances world modeling through model scaling and data scaling. For model scaling, a single model with shared weights exposes three control interfaces: a policy (world-action model), a simulator (action-conditioned world model), and an evaluator (value model). The policy proposes candidate action chunks, the simulator predicts their visual consequences, and the evaluator assesses the predicted outcomes. Their coupling forms a closed decision-and-learning loop for policy improvement. This formulation uses curated expert demonstrations for action learning, while failed and suboptimal interactions provide valuable evidence for dynamics modeling and value learning. For data scaling, Motus2 progresses from large-scale monocular egocentric data to synchronized stereo egocentric data, followed by robot-domain adaptation with robot trajectories and supplementary human-robot alignment data. Motus2 further studies global-autoregressive and hybrid-memory extensions of its sliding-window context, adds tactile feedback for contact-aware control, and is instantiated on a fully biomimetic platform with stereo vision, dual arms, dual dexterous hands, and tactile sensing. Together, egocentric data scaling and closed-loop general world model scaling provide a general path toward self-evolving dexterous manipulation.

Related papers

• Predicting Consequences and Reinforcing Navigation Policies with Latent World Models [31.865100130203317]
  We propose a compatibility prediction Latent World Model (LWM) for robot navigation.<n>Our key insight is that spatial proximity correlates with latent feature similarity, enabling action consequences to be evaluated directly in latent space.<n>Our approach significantly outperforms prior world model and imitation learning methods in prediction accuracy, policy learning, and real-world navigation performance.
  arXiv  Detail & Related papers  (2026-08-23T11:58:42Z)
• Learning Transferable Dynamics Priors from Action to World Modeling [22.976971391971617]
  We study action-conditioned world modeling as a scalable way to learn transferable dynamics priors for robot learning.<n>By pretraining a model to predict how actions drive visual scene evolution, the resulting world model captures reusable interaction dynamics beyond appearance-level video generation.<n> Experiments across simulation benchmarks and real-robot settings demonstrate that action-conditioned world model pretraining yields transferable dynamics priors.
  arXiv  Detail & Related papers  (2026-06-28T17:01:55Z)
• WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform [130.8118909583659]
  We introduce WorldArena 2.0, an expanded benchmark for embodied world model evaluation.<n>WorldArena 2.0 systematically broadens embodied world model evaluation along three dimensions: modality, functionality, and platform.<n>Under a standardized protocol, WorldArena 2.0 comprehensively evaluates perceptual quality, interactive utility, and cross-platform performance.
  arXiv  Detail & Related papers  (2026-05-18T06:18:21Z)
• HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models [58.191567345416836]
  World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics.<n>HarmoWAM fully leverages a world model to unify predictive and reactive control, enabling both general transit and precise manipulation.<n>We construct three training-unseen test environments across six real-world robotic tasks, covering variations in background, position, and object semantics.
  arXiv  Detail & Related papers  (2026-05-11T17:59:56Z)
• MotuBrain: An Advanced World Action Model for Robot Control [23.733029557644354]
  We present MotuBrain, a unified World Action Model that jointly models video and action under a UniDiffuser formulation.<n>A single model supports policy learning, world modeling, video generation, inverse dynamics, and joint video-action prediction.<n>Building on Motus, MotuBrain further introduces unified multiview modeling, an independent text stream for stronger language-action coupling.<n>Our inference stack combines step reduction, compilation, FP8 quantization, DiT caching, V2A-style action-only inference, and real-time chunked closed-loop execution.
  arXiv  Detail & Related papers  (2026-04-30T12:34:44Z)
• Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond [209.35045331678043]
  We introduce a "levels x laws" taxonomy organized along two axes.<n>The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence.<n>We synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery.
  arXiv  Detail & Related papers  (2026-04-24T17:48:47Z)
• Causal World Modeling for Robot Control [56.31803788587547]
  Video world models provide the ability to imagine the near future by understanding the causality between actions and visual dynamics.<n>We introduce LingBot-VA, an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously.<n>We evaluate our model on both simulation benchmarks and real-world scenarios, where it shows significant promise in long-horizon manipulation, data efficiency in post-training, and strong generalizability to novel configurations.
  arXiv  Detail & Related papers  (2026-01-29T17:07:43Z)
• Motus: A Unified Latent Action World Model [31.62340897751899]
  We propose Motus, a unified latent action world model that leverages existing general pretrained models and rich, sharable motion information.<n>Experiments show that Motus achieves superior performance against state-of-the-art methods in both simulation and real-world scenarios.
  arXiv  Detail & Related papers  (2025-12-15T06:58:40Z)
• A Comprehensive Survey on World Models for Embodied AI [14.457261562275121]
  Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states.<n>This survey presents a unified framework for world models in embodied AI.
  arXiv  Detail & Related papers  (2025-10-19T07:12:32Z)
• DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model [65.43473733967038]
  We introduce DrivingDojo, the first dataset tailor-made for training interactive world models with complex driving dynamics. Our dataset features video clips with a complete set of driving maneuvers, diverse multi-agent interplay, and rich open-world driving knowledge.
  arXiv  Detail & Related papers  (2024-10-14T17:19:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.