ACE: Agentic Control for Embodied Manipulation via Zero-shot Workflow Reasoning

Excerpt

arXiv:2607.04162v2 Announce Type: replace-cross Abstract: General-purpose manipulation requires both semantic reasoning over task constraints and reliable execution of contact-rich actions. We present ACE, an agentic manipulation harness that composes a high-level language agent with a reusable mask-conditioned visuomotor policy. Given an open-ended instruction, the agent solves semantic constraints, binds objects to destination roles, and decomposes the task into executable transfers represente