SOURCE-LINKED INTELLIGENCE

Benchmarking World Models for Continual Learning on Compositional Tasks

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

A desirable property of a world model is the ability to learn continually across tasks, adapting to new environments without forgetting what the agent has already learnt. In particular, the ability to retain and reuse knowledge obtained from prior experiences underpins an agent's ability to efficiently adapt to novel environments, as the dynamics of the physical world can often be described in recurring mechanisms. However, the world model's measure of adaptation entangles two abilities: the speed and capacity to learn unseen tasks, and the reuse of knowledge already acquired, since incoming t

Read original source ↗ Open in workspace

recordType

paper

region

Global