# AR-WAM: A Visual-Conditioned Agent-Ready World Action Model for Robotic Manipulation

arXiv: https://arxiv.org/abs/2609.23578 · HTML: https://mlsanity.com/paper/2609.23578/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 19 of its 51 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 19 of 19)

- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation](https://mlsanity.com/paper/2410.06158/) (2024)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [Kimi K3: Open Frontier Intelligence](https://mlsanity.com/paper/2607.24653/) (2026)
- [DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping](https://mlsanity.com/paper/2502.20900/) (2025)
- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies](https://mlsanity.com/paper/2606.15768/) (2026)
- [Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents](https://mlsanity.com/paper/2607.08448/) (2026)
- [RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Design](https://mlsanity.com/paper/2603.01229/) (2026)
- [VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models](https://mlsanity.com/paper/2603.22003/) (2026)
- [Do You Need Proprioceptive States in Visuomotor Policies?](https://mlsanity.com/paper/2509.18644/) (2025)
- [MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models](https://mlsanity.com/paper/2606.13515/) (2026)
- [Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection](https://mlsanity.com/paper/2604.13942/) (2026)
- [Point What You Mean: Visually Grounded Instruction Policy](https://mlsanity.com/paper/2512.18933/) (2025)
- [LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation](https://mlsanity.com/paper/2608.03701/) (2026)
- [Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation](https://mlsanity.com/paper/2607.05377/) (2026)

## Abstract (arXiv)

As AI agents become increasingly capable, agent-driven robotic control is emerging as a compelling paradigm. However, prevailing vision-language-action (VLA) models and world action models (WAMs) still rely on natural-language instructions to specify manipulation tasks, an ill-suited interface for agent-driven control: referentially ambiguous, spatially imprecise, redundant with the agent's inherent language understanding, and entangling intent with execution. We present AR-WAM, a visual-conditioned, agent-ready world action model that replaces language with two complementary conditions: a visual grounding prompt (a bounding box of the target) denoting the interaction object and location, and a learnable operation token dictating the atomic skill to execute. Our compact 0.5B-parameter model, with a frozen pretrained visual encoder and no language encoder, predicts scene evolution within compact latent states while decoding actions, exposing the policy's intent through explicit, supervisable reasoning signals. A model-agnostic compatibility layer provides three primitives (detect, execute, and query) so that local VLMs or online agent APIs can drive the policy directly, with long-horizon memory and closed-loop error recovery delegated to the agent side. On RoboTwin 2.0, RMBench, and a real Astribot S1 dual-arm platform, AR-WAM attains the highest average success on standard manipulation (85.7% over the clean and randomized settings) and outperforms all baselines on memory-dependent and real-robot long-horizon tasks, improving success rates by 5.9% and 36.7%, respectively, while maintaining the lowest inference latency (14.1 ms). Project page is at https://ar-wam.github.io/.