梳理流式大模型定义与分类，推动实时交互应用发展
From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models
- 提出统一的流式大模型定义，明确数据流与动态交互核心
- 构建系统性分类框架，涵盖生成、输入与架构三类流式模式
- 适合关注实时AI交互、智能系统设计的研究者与工程师
标准大语言模型主要面向静态推理，输入固定，难以适应动态实时场景。为此，流式大模型范式应运而生。然而现有定义零散，常将流式生成、流式输入与交互式架构混为一谈，缺乏系统性分类。本文首次基于数据流与动态交互建立统一定义，澄清概念模糊。在此基础上，提出一套系统性分类体系，并深入分析各类方法原理。同时探讨其在真实场景中的应用潜力，展望未来研究方向。作者维护持续更新的论文库：https://github.com/EIT-NLP/Awesome-Streaming-LLMs。
原文摘要 · Abstract (English)
Standard Large Language Models (LLMs) are predominantly designed for static inference with pre-defined inputs, which limits their applicability in dynamic, real-time scenarios. To address this gap, the streaming LLM paradigm has emerged. However, existing definitions of streaming LLMs remain fragmented, conflating streaming generation, streaming inputs, and interactive streaming architectures, while a systematic taxonomy is still lacking. This paper provides a comprehensive overview and analysis of streaming LLMs. First, we establish a unified definition of streaming LLMs based on data flow and dynamic interaction to clarify existing ambiguities. Building on this definition, we propose a systematic taxonomy of current streaming LLMs and conduct an in-depth discussion on their underlying methodologies. Furthermore, we explore the applications of streaming LLMs in real-world scenarios and outline promising research directions to support ongoing advances in streaming intelligence. We maintain a continuously updated repository of relevant papers at https://github.com/EIT-NLP/Awesome-Streaming-LLMs.
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。