Modular Cognitive Architecture Emerges in Large Language Models

• 类型：arxiv
• 标识：2608.13567
• 链接：https://arxiv.org/abs/2608.13567
• 主分类：llm-infra
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：Using circuit analyses across N=46 tasks spanning four cognitive domains, it is found that Large Language Models 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.
• 待LLM分类：否
• 标题中文：模块化认知架构在 Large Language Models 中涌现
• TLDR中文：通过跨 46 个任务（涵盖四个认知领域）的电路分析，发现 LLM 发展出与人类大脑相似的模块化架构：在人类大脑中依赖同一网络的任务会在 LLM 中招募重叠的神经元，而依赖不同网络的任务则招募不同的神经元。
• 成熟度：research
• 场景：cognitive-architecture、llm
• 来源文件：
• /inbox/tom/_candidates/2026-08-18-rag-retrieval-reranking-candidates.json
• [S2 enrich]