English

Software-Defined Agentic Serving

Distributed, Parallel, and Cluster Computing 2026-01-07 v1 Multiagent Systems

Abstract

As multi-agent LLM pipelines grow in complexity, existing serving paradigms fail to adapt to the dynamic serving conditions. We argue that agentic serving systems should be programmable and system-aware, unlike existing serving which statically encode the parameters. In this work, we propose a new SDN-inspired agentic serving framework that helps control the key attributes of communication based on runtime state. This architecture enables serving-efficient, responsive agent systems and paves the way for high-level intent-driven agentic serving.

Keywords

Cite

@article{arxiv.2601.03197,
  title  = {Software-Defined Agentic Serving},
  author = {Saurabh Agarwal and Marco Laju and Jayanth Srinivasa and Myungjin Lee and Aditya Akella},
  journal= {arXiv preprint arXiv:2601.03197},
  year   = {2026}
}