Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent

Paper recorded by Signals 4 on 2026-10-26 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-26 on arXiv · recorded by Signals 4 on 2026-10-27

Category: cs.AI · 人工智能 · first seen 2026-10-27

Abstract

A robot policy needs to understand what a task is asking for in a scene, and how to move the robot to accomplish that task. To achieve these two skills, we introduce Zero-real Agent Policy (ZAP), a recipe that teaches a small off-the-shelf vision-language model to control a robot via a simple tool harness. We use a pretrained 27B parameter model to bootstrap world understanding and reasoning, foll

Read on arXiv →