English

Grokking From Abstraction to Intelligence

Artificial Intelligence 2026-04-01 v1

Abstract

Grokking in modular arithmetic has established itself as the quintessential fruit fly experiment, serving as a critical domain for investigating the mechanistic origins of model generalization. Despite its significance, existing research remains narrowly focused on specific local circuits or optimization tuning, largely overlooking the global structural evolution that fundamentally drives this phenomenon. We propose that grokking originates from a spontaneous simplification of internal model structures governed by the principle of parsimony. We integrate causal, spectral, and algorithmic complexity measures alongside Singular Learning Theory to reveal that the transition from memorization to generalization corresponds to the physical collapse of redundant manifolds and deep information compression, offering a novel perspective for understanding the mechanisms of model overfitting and generalization.

Keywords

Cite

@article{arxiv.2603.29262,
  title  = {Grokking From Abstraction to Intelligence},
  author = {Junjie Zhang and Zhen Shen and Gang Xiong and Xisong Dong},
  journal= {arXiv preprint arXiv:2603.29262},
  year   = {2026}
}

Comments

22page and 5 figures,In this paper, we analyze the grokking phenomenon from the perspective of Singular Learning Theory (SLT). This work is currently under review for ICML 2026

R2 v1 2026-07-01T11:45:29.986Z