Saved in:
Bibliographic Details
Main Authors: Tong, Junlong, Wang, Zilong, Ren, YuJie, Yin, Peiran, Wu, Hao, Zhang, Wei, Shen, Xiaoyu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.04592
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917419716444160
author Tong, Junlong
Wang, Zilong
Ren, YuJie
Yin, Peiran
Wu, Hao
Zhang, Wei
Shen, Xiaoyu
author_facet Tong, Junlong
Wang, Zilong
Ren, YuJie
Yin, Peiran
Wu, Hao
Zhang, Wei
Shen, Xiaoyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_04592
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models
Tong, Junlong
Wang, Zilong
Ren, YuJie
Yin, Peiran
Wu, Hao
Zhang, Wei
Shen, Xiaoyu
Computation and Language
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.
title From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2603.04592