Do Language Models Track Entities Across State Changes?

ArXi:2605.30233v1 Announce Type: cross Entity tracking (ET), the ability to keep track of states, is a fundamental skill that underlies complex reasoning. An increasing amount of work investigates how transformer language models (LMs) solve entity binding $\textit{without}$ state changes. However, there is limited understanding of how non-toy LMs address ET problems of realistic difficulties expressed in natural language. To this end, we investigate the mechanisms underlying ET in complex scenarios featuring multiple state-changing operations.