Spontaneous Functional Differentiation in Large Language Models: A Brain-Like Intelligence Economy

📅 2026-03-31
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study investigates whether large language models spontaneously develop brain-like functional specialization to support high-level cognition. By applying integrated information decomposition, the authors systematically quantify information synergy and redundancy across layers in diverse architectures. They report the first evidence that intermediate layers undergo a phase-transition-like emergence of highly synergistic cores during complex tasks, while early and late layers predominantly rely on redundant processing, collectively forming a dynamic, brain-inspired organization. Ablation experiments demonstrate that this synergistic structure is critical for abstract reasoning, as its removal leads to catastrophic performance degradation, thereby establishing it as a core physical substrate of model intelligence. These findings offer novel empirical support for bridging artificial and biological intelligence.
📝 Abstract
The evolution of intelligence in artificial systems provides a unique opportunity to identify universal computational principles. Here we show that large language models spontaneously develop synergistic cores where information integration exceeds individual parts remarkably similar to the human brain. Using Integrated Information Decomposition across multiple architectures we find that middle layers exhibit synergistic processing while early and late layers rely on redundancy. This organization is dynamic and emerges as a physical phase transition as task difficulty increases. Crucially ablating synergistic components causes catastrophic performance loss confirming their role as the physical entity of abstract reasoning and bridging artificial and biological intelligence.
Problem

Research questions and friction points this paper is trying to address.

spontaneous differentiation
large language models
integrated information
synergistic processing
brain-like intelligence
Innovation

Methods, ideas, or system contributions that make the work stand out.

synergistic cores
Integrated Information Decomposition
phase transition
abstract reasoning
brain-like intelligence
🔎 Similar Papers
No similar papers found.
J
Junjie Zhang
Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences
Zhen Shen
Zhen Shen
Institute of Automation, Chinese Academy of Sciences
Parallel IntelligenceIntelligent Control3D PrintingIntelligent Manufacturing
Gang Xiong
Gang Xiong
Institute of Automation,Chinese Academy of Sciences
Intelligent Control and ManagementIntelligent Transportation SystemsIntelligent Manufacturing
X
Xisong Dong
Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences