SOURCE-LINKED INTELLIGENCE

Beyond Task Success: Stage-Wise Reliability of World Model Planning under Sensing Degradation

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

In world model planning, sensing inputs pass through an encoder and predictor before affecting planner decisions, so final task success alone cannot reveal where sensing disturbances attenuate or persist in the pipeline. We apply 10 visual and temporal sensing degradations to a world model planner and track their effects across representation, future prediction, planner preference, and physical outcome using paired evaluation on the same 50 tasks. The relative impact of degradations was not preserved across stages: large representation shifts could attenuate downstream, while smaller initial s

Read original source ↗ Open in workspace

recordType

paper

region

Global