Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System
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.
Key points
- 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.
Sources (1)
- [1]Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent SystemarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 01:05 PM
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.
Extractive summary: sentences quoted from the sources.