SOURCE-LINKED INTELLIGENCE

FARM: Reading Failure Signals from the Internal Predictive States of a Frozen Robotic World Model

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Reliable robot deployment requires online failure monitoring, yet existing monitors mainly derive risk from proxy signals or train dedicated monitoring components. We ask whether the internal predictive states of a frozen pretrained robotic world model already contain directly decodable failure information. Failure-Aware Readout from World Models (FARM) trains only a 33,985-parameter supervised readout over frozen VLA-JEPA predictive states, producing step-wise failure scores and causal trajectory risk. Five-fold out-of-fold evaluation across seven source tasks reaches 85.68/88.59 pooled AUROC

Read original source ↗ Open in workspace

recordType

paper

region

Global