AI RESEARCH
From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models
arXiv CS.CL
•
ArXi:2603.04592v2 Announce Type: replace 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.