SOURCE-LINKED INTELLIGENCE

How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account

arXiv · AI, language, vision and robotics · article · Aug 30, 2026 · UTC

How do LLM agents come to both understand environments they act in and master tasks set within them? Through controlled experiments combining world-model training (next-state prediction) and policy training (reward maximization), we investigate this question. We dissect the resulting models through their additive parameter updates. Geometrically, we find effective world-model updates are low-rank and share an input-feature subspace with policy updates while writing to nearly orthogonal output directions, whether trained separately or sequentially. However, we find that, in projection intervent

Read original source ↗ Open in workspace

recordType

paper

region

Global