Paper
Evidence of an Emergent "Self" in Continual Robot Learning
Authors
Adidev Jhunjhunwala, Judah Goldfeder, Hod Lipson
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 principle to analyze the cognitive structure of robots under two conditions: One robot learns a constant task, while a second robot is subjected to continual learning under variable tasks. We find that robots subjected to continual learning develop an invariant subnetwork that is significantly more stable (p < 0.001) compared to the control. We suggest that this principle can offer a window into exploring selfhood in other cognitive AI systems.
Metadata
Related papers
Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini
Ruofei Du, Benjamin Hersh, David Li, Nels Numan, Xun Qian, Yanhe Chen, Zhongy... • 2026-03-25
Comparing Developer and LLM Biases in Code Evaluation
Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donah... • 2026-03-25
The Stochastic Gap: A Markovian Framework for Pre-Deployment Reliability and Oversight-Cost Auditing in Agentic Artificial Intelligence
Biplab Pal, Santanu Bhattacharya • 2026-03-25
Retrieval Improvements Do Not Guarantee Better Answers: A Study of RAG for AI Policy QA
Saahil Mathur, Ryan David Rittner, Vedant Ajit Thakur, Daniel Stuart Schiff, ... • 2026-03-25
MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination
Zhuo Li, Yupeng Zhang, Pengyu Cheng, Jiajun Song, Mengyu Zhou, Hao Li, Shujie... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.24350v1</id>\n <title>Evidence of an Emergent \"Self\" in Continual Robot Learning</title>\n <updated>2026-03-25T14:27:32Z</updated>\n <link href='https://arxiv.org/abs/2603.24350v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.24350v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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 principle to analyze the cognitive structure of robots under two conditions: One robot learns a constant task, while a second robot is subjected to continual learning under variable tasks. We find that robots subjected to continual learning develop an invariant subnetwork that is significantly more stable (p < 0.001) compared to the control. We suggest that this principle can offer a window into exploring selfhood in other cognitive AI systems.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n <published>2026-03-25T14:27:32Z</published>\n <arxiv:comment>39 pages, 17 figures, includes supplementary materials</arxiv:comment>\n <arxiv:primary_category term='cs.RO'/>\n <author>\n <name>Adidev Jhunjhunwala</name>\n </author>\n <author>\n <name>Judah Goldfeder</name>\n </author>\n <author>\n <name>Hod Lipson</name>\n </author>\n </entry>"
}