从 LLM 聊天到自主 AI 智能体：LLM 集成应用的七种形态

Authors:Irene Weber (University of Applied Sciences Kempten, Germany)

Abstract:Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-augmented generation, workflow, coding agent and AI agent. Whether these labels denote genuine architectural forms or serve as branding has not been assessed systematically.
In the sources surveyed, labels do carry architectural content, most clearly in vendor usage: copilot denotes a router-worker architecture operating a host application under step-by-step user confirmation, while the more recent shift to the label agent coincides with AI-planned multi-step execution of which the user sees only the outcome. The coding agents of four major providers share one architecture, a reason-and-act loop delegating to subagents.
This survey describes seven recurring forms---LLM chats, custom agents, retrieval-augmented generation (RAG), AI-enhanced workflows, copilots, coding agents, and, in part, agentic RAG---in a common vocabulary of agents and tools. Each is characterized along four structural dimensions (agentic RAG only partially): the architectural pattern, the control of execution and the point of user intervention, the number of agent calls per task, and tool use. An illustrative corpus of 22 systems from research publications and vendor documentation grounds the descriptions and shows where they reach their limit.

Subjects:	Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
ACM classes:	I.2.11; D.2.11; I.2.7
Cite as:	arXiv:2610.11899 [cs.CL]
	(or arXiv:2610.11899v1 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2610.11899 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Irene Weber [view email]
[v1] Thu, 8 Oct 2026 13:05:33 UTC (101 KB)