AI RESEARCH
Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective
arXiv CS.AI
•
ArXi:2603.16104v1 Announce Type: cross Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and intermediate results due to speculative and parallel exploration. Existing LLM serving systems, such as vLLM, focus on optimizing individual inference calls and overlook cross-call dependencies, leading to significant inefficiencies. This paper rethinks LLM and agent serving from a data systems perspective and.