Representation alignmentExpert
On Representational Alignment among Embodied Agents
This preprint formalizes a task-dependent stopping condition for aligning representations across embodied agents. In an analytical hand-off scenario, the same ambiguity needs zero added sensorimotor anchors for relative synchronization but exactly one for absolute timing, because only the interaction invariance changes. This matters for multi-robot and human-robot systems: it suggests targeting alignment effort only where unresolved differences can change the task outcome.