Generalist AI agents controlling robots directly outperform specialist manipulation policies by 15-20x in failure rates, and can learn from experience with memory—suggesting agentic approaches are more robust and general than task-specific models.
This paper shows that generalist AI models can control robot manipulators more reliably than specialist policies by using agentic manipulation policies (AMPs)—where an AI agent directly commands the robot and adapts actions in real-time. AMP1, their reference system, achieves 85.6% zero-shot success on RoboLab-120 (vs.