# World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal

arXiv: https://arxiv.org/abs/2609.29964 · HTML: https://mlsanity.com/paper/2609.29964/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 31 of its 39 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 31)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models](https://mlsanity.com/paper/2502.19417/) (2025)
- [LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization](https://mlsanity.com/paper/2510.03827/) (2025)
- [HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation](https://mlsanity.com/paper/2502.05485/) (2025)
- [CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation](https://mlsanity.com/paper/2603.22435/) (2026)
- [OmniManip: Towards General Robotic Manipulation via Object-Centric Interaction Primitives as Spatial Constraints](https://mlsanity.com/paper/2501.03841/) (2025)
- [RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis](https://mlsanity.com/paper/2402.16117/) (2024)
- [Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting](https://mlsanity.com/paper/2509.22195/) (2025)
- [Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents](https://mlsanity.com/paper/2607.08448/) (2026)
- [From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation](https://mlsanity.com/paper/2505.08548/) (2025)
- [RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation](https://mlsanity.com/paper/2402.14623/) (2024)
- [Playful Agentic Robot Learning](https://mlsanity.com/paper/2606.19419/) (2026)
- [Show-Harness: Just a VLM Agent Can Play Robots](https://mlsanity.com/paper/2609.10522/) (2026)
- [MMSkills: Towards Multimodal Skills for General Visual Agents](https://mlsanity.com/paper/2605.13527/) (2026)
- [GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks](https://mlsanity.com/paper/2607.05369/) (2026)
- [Agent as Policy for Robotic Manipulation](https://mlsanity.com/paper/2609.12541/) (2026)
- [VIA: Visual Interface Agent for Robot Control](https://mlsanity.com/paper/2607.11119/) (2026)
- [VISUALSKILL: Multimodal Skills for Computer-Use Agents](https://mlsanity.com/paper/2606.18448/) (2026)

## Built on by (most cited first, 2 of 2)

- [In-Context Learning for Robots: Methods and Applications](https://mlsanity.com/paper/2609.36012/) (2026)
- [Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena](https://mlsanity.com/paper/2610.00854/) (2026)

## Abstract (arXiv)

General-purpose vision-language models (VLMs) bring broad knowledge and spatial reasoning to robot manipulation, yet existing systems either use them indirectly, to predict constraints or write programs, or give them a view of the scene rather than a world in which to act. We present World Action Agent (WAA), a multi-agent harness through which VLMs pilot robots with basic tools, making every decision within a visual action workspace. The workspace has three properties. Contact views, selected automatically from the scene geometry, present the scene around the current interaction. Action rehearsal turns each action into an editable proposal that the agent, alone or through an Imagination Agent, previews and revises against planning feedback before execution. In-view correction closes the loop between observation, rehearsal, and low-level execution, letting the agent remove residual offsets in the view where it observes them. Through the same workspace, WAA acquires embodied procedural knowledge in two ways: it evolves multimodal skills from expert videos and human teaching under evidence-based review and consults them through a Skill Agent, and its interaction traces train smaller VLMs to pilot the same harness. On LIBERO-Pro, WAA with skills evolved only from LIBERO-90 reaches a state-of-the-art 75.6% average success, outperforming end-to-end VLAs, code-as-policy agents, and a visual-harness baseline with the same backbone; the same skills remain effective on robosuite without further learning. Fine-tuning Qwen3.5-9B on harness traces raises its out-of-domain success from 1.7% to 43.3%.