Apple Framework Lets General AI Models Control Robot Arms Zero-Shot at 85.6%

1 reports archived1 independent sourcesupdated 11/10/2026, 07:43:42

Synthesis & Latest Updates

1 Sources Cross-Validated

A new Apple paper introduces AMP1, a harness that lets general-purpose frontier models such as Claude Opus 5.5 and Gemini 4 Argon control a robot arm in a closed loop using camera views, code execution and direct motion commands, with no demonstrations or task-specific training. It achieves 85.6% zero-shot success on RoboLab-120 versus 49.2% for the best VLA and 42.9% for the best world-action model, and succeeds in 104 of 108 trials on a real Franka arm, though the robot idles much of each episode waiting on model inference.

LATEST/A new Apple paper introduces AMP1, a harness that lets general-purpose frontier models such as Claude Opus 5.5 and Gemini 4 Argon control a robot arm in a closed loop using camera views, code execution and direct motion commands, with no demonstrations or task-specific training. It achieves 85.6% zero-shot success on RoboLab-120 versus 49.2% for the best VLA and 42.9% for the best world-action model, and succeeds in 104 of 108 trials on a real Franka arm, though the robot idles much of each episode waiting on model inference.

Hourly heat curve

3 fully observed hours

Now

16.1

Peak

16.608:00

24h change

–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first

Rohan Paul (@rohanpaul_ai)T2Nov 10, 07:43·78 pts
Apple Framework Lets General AI Models Control Robot Arms Zero-Shot at 85.6%
- AMP1 ships with no built-in grasping or placing skills; the model invents its own strategies and hits 85.6% zero-shot, far ahead of specialist VLA models
- On a real Franka arm it succeeded in 104 of 108 trials, showing transfer from benchmark to hardware
- Inference latency is the main bottleneck, with the robot idling much of each episode
View Related Reports & Analysis Original Source