From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Jiayi, Ye, Junyi, Wang, Guiling
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914544082747392
author Chen, Jiayi
Ye, Junyi
Wang, Guiling
author_facet Chen, Jiayi
Ye, Junyi
Wang, Guiling
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04565
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
Chen, Jiayi
Ye, Junyi
Wang, Guiling
Multiagent Systems
Computation and Language
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.
title From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
topic Multiagent Systems
Computation and Language
url https://arxiv.org/abs/2506.04565