Quantifies an emergent 'self' in robots as an invariant subnetwork that persists across continual learning of variable tasks.
March 26, 2026
Original Paper
Evidence of an Emergent "Self" in Continual Robot Learning
arXiv · 2603.24350
The Takeaway
This paper offers a principled, quantifiable definition of 'selfhood' in AI by isolating stable cognitive structures from volatile skill acquisition. It challenges how we evaluate agent identity and provides a metric for observing the development of internal invariants in autonomous systems.
From the abstract
A key challenge to understanding self-awareness has been a principled way of quantifying whether an intelligent system has a concept of a "self," and if so how to differentiate the "self" from other cognitive structures. We propose that the "self" can be isolated by seeking the invariant portion of cognitive process that changes relatively little compared to more rapidly acquired cognitive knowledge and skills, because our self is the most persistent aspect of our experiences. We used this princ