SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

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 rehea

Read original source ↗ Open in workspace

recordType

paper

region

Global