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

  • 类型:arxiv
  • 标识:2609.29964
  • 链接:https://arxiv.org/abs/2609.29964
  • 主分类:agent
  • 形态:method
  • TLDR: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
  • 副分类:evaluation
  • 待LLM分类:否
  • 来源文件:
  • /inbox/tom/_candidates/2026-09-25-agent-rag-longcontext-candidates.json