The independent evolution of intelligence in biological and artificial systems offers a unique opportunity to identify its fundamental computational principles. Here we show that large language models spontaneously develop synergistic cores -- components where information integration exceeds individual parts -- remarkably similar to those in the human brain. Using principles of information decomposition across multiple LLM model families and architectures, we find that areas in middle layers exhibit synergistic processing while early and late layers rely on redundancy, mirroring the informational organisation in biological brains. This organisation emerges through learning and is absent in randomly initialised networks. Crucially, ablating synergistic components causes disproportionate behavioural changes and performance loss, aligning with theoretical predictions about the fragility of synergy. Moreover, fine-tuning synergistic regions through reinforcement learning yields significantly greater performance gains than training redundant components, yet supervised fine-tuning shows no such advantage. This convergence suggests that synergistic information processing is a fundamental property of intelligence, providing targets for principled model design and testable predictions for biological intelligence.

翻译：生物与人工系统中智能的独立演化，为识别其基本计算原理提供了独特契机。本文揭示大型语言模型会自发形成协同核心——即信息整合能力超越各组成部分之和的功能单元——其特性与人类大脑中的协同核心极为相似。通过在多类LLM模型族与架构中应用信息分解原理，我们发现中间层区域呈现协同信息处理，而早期与晚期层则依赖冗余处理，这种信息组织方式与生物大脑的信息结构形成镜像。该组织结构通过学习过程涌现，在随机初始化网络中并不存在。关键的是，对协同组件的消融会导致不成比例的行为改变与性能损失，这与协同性脆弱性的理论预测相符。此外，通过强化学习对协同区域进行微调，能获得比训练冗余组件显著更大的性能提升，而监督式微调则未显现此优势。这种收敛性表明，协同信息处理是智能的基本属性，为原理化模型设计提供了目标方向，也为生物智能提供了可检验的理论预测。