整合大模型与外部组件，构建更智能的系统级AI
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
- 将大模型与检索、工具等模块组合成协同工作流
- 提出多维度分类框架，梳理四种核心系统范式
- 适合研究系统级AI的学者与开发智能应用的工程师
复合人工智能系统（CAIS）是一种新兴范式，通过将大语言模型（LLMs）与检索器、代理、工具和编排器等外部组件集成，克服独立模型在记忆、推理、实时定位和多模态理解任务中的局限。这些系统通过组合多个专用模块形成连贯工作流，实现更强大、上下文感知的行为。尽管学术界和工业界广泛应用，但CAIS领域仍缺乏统一分析、分类与评估框架。本文定义了CAIS概念，基于组件角色与编排策略提出多维分类体系，分析四种基础范式：检索增强生成（RAG）、大模型代理、多模态大模型（MLLMs）与编排系统。综述代表性系统，比较设计权衡，总结评估方法。最后指出可扩展性、互操作性、基准测试与协调等关键挑战，并展望未来研究方向。本综述旨在为研究人员与实践者提供系统级人工智能发展的全面基础。
原文摘要 · Abstract (English)
Compound AI Systems (CAIS) are an emerging paradigm that integrates large language models (LLMs) with external components, including retrievers, agents, tools, and orchestrators, to overcome the limitations of standalone models in tasks requiring memory, reasoning, real-time grounding, and multimodal understanding. These systems enable more capable and context-aware behaviors by composing multiple specialized modules into cohesive workflows. Despite growing adoption in both academia and industry, the CAIS landscape remains fragmented and lacks a unified framework for analysis, taxonomy, and evaluation. In this survey, we define the concept of CAIS, propose a multi-dimensional taxonomy based on component roles and orchestration strategies, and analyze four foundational paradigms: Retrieval-Augmented Generation (RAG), LLM Agents, Multimodal LLMs (MLLMs), and Orchestration. We review representative systems, compare design trade-offs, and summarize evaluation methodologies across these paradigms. Finally, we identify key challenges - including scalability, interoperability, benchmarking, and coordination - and outline promising directions for future research. This survey aims to provide researchers and practitioners with a comprehensive foundation for understanding, developing, and advancing the next generation of system-level artificial intelligence.
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。