AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

The Right Future for Action: Learning Action-Relevant Predictive States in World Action Models

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Generation-free world action models (WAMs) retain future-video prediction during training but act from internal video features at inference, leaving unclear what these features should preserve for control. Our representation diagnostics show that representations with more predictable future changes need not make linear action decoding easier. Observed future changes provide additional action information beyond the present, and linearly readable action information is spatially concentrated. These findings motivate Action-Relevant Predictive States (ARPS), a compact predictive interface between

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-23T10:01:48.231Z. This is not the publication date.