借鉴计算机系统设计，构建更通用可扩展的LLM智能体
Building LLM Agents by Incorporating Insights from Computer Systems
- 从冯·诺依曼架构出发，提出模块化、可复用的LLM智能体框架
- 系统梳理现有智能体设计缺陷，识别出通用性与可扩展性不足的核心问题
- 适合对智能体架构设计感兴趣的研究者和系统级开发者
近年来，基于大语言模型的自主智能体成为热门方向。然而，多数此类智能体的设计依赖经验或直觉，缺乏系统性原则，导致结构多样但通用性与可扩展性有限。本文主张借鉴计算机系统设计思想来构建LLM智能体。受冯·诺依曼体系结构启发，提出一种结构化的LLM智能体系统框架，强调模块化设计与通用原则。论文首先从计算机系统视角全面回顾了LLM智能体，接着识别出由系统设计启发的关键挑战与未来方向，并探索了超越计算机系统的智能体学习机制。该对比分析所得洞见为智能体的系统化设计与演进奠定了基础。
原文摘要 · Abstract (English)
LLM-driven autonomous agents have emerged as a promising direction in recent years. However, many of these LLM agents are designed empirically or based on intuition, often lacking systematic design principles, which results in diverse agent structures with limited generality and scalability. In this paper, we advocate for building LLM agents by incorporating insights from computer systems. Inspired by the von Neumann architecture, we propose a structured framework for LLM agentic systems, emphasizing modular design and universal principles. Specifically, this paper first provides a comprehensive review of LLM agents from the computer system perspective, then identifies key challenges and future directions inspired by computer system design, and finally explores the learning mechanisms for LLM agents beyond the computer system. The insights gained from this comparative analysis offer a foundation for systematic LLM agent design and advancement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。