Modular Cognitive Architecture Emerges in Large Language Models
The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental principle of how intelligent systems must be built, or an evolutionary accident specific to biological brains? Here, we test whether a similar organization emerges in Large Language Models--another class of intelligent systems created through a very different optimization process. Using circuit analyses across N=46 tasks spanning four cognitive domains (language, formal reasoning, social reasoning, physical reasoning), we find that LLMs develop a modular architecture that mirrors the human brain: tasks drawing on the same network in humans recruit overlapping neurons in LLMs, whereas tasks drawing on different networks recruit distinct neurons. The convergent emergence of modularity in brains and neural networks suggests that it may be a fundamental property of intelligent systems.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ModuleFormer: Modularity Emerges from Mixture-of-Experts
Large Language Models (LLMs) have achieved remarkable results. However, existing models are expensive to train and deploy, and it is also difficult to expand their knowledge beyond pre-training data without forgetting pr…
Language ModellingLightweight DeploymentMixture-of-ExpertsA Modular Cognitive Architecture for Assisted Reasoning: The Nemosine Framework
This paper presents the Nemosine Framework, a modular cognitive architecture designed to support assisted reasoning, structured thinking, and systematic analysis. The model operates through functional cognitive modules (…
A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems
Large Language Models-Cognitive Assistants (LLM-CAs) can enhance Quality Management Systems (QMS) in manufacturing, fostering continuous process improvement and knowledge management. However, there is no human-centred so…
Omega: An Architecture for AI Unification
We introduce the open-ended, modular, self-improving Omega AI unification architecture which is a refinement of Solomonoff's Alpha architecture, as considered from first principles. The architecture embodies several cruc…
DiversityOmega: An Architecture for AI Unification
We introduce the open-ended, modular, self-improving Omega AI unification architecture which is a refinement of Solomonoff's Alpha architecture, as considered from first principles. The architecture embodies several cruc…
Diversity