AI RESEARCH
VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?
arXiv CS.AI
•
ArXi:2605.06068v1 Announce Type: new For years, we have built LLM serving systems like any other critical infrastructure: a single general-purpose stack, hand-tuned over many engineer-years, meant to every model and workload. In this paper, we take the opposite bet: a multi-agent loop that automatically synthesizes bespoke serving systems for different usage scenarios. We propose VibeServe, the first agentic loop that generates entire LLM serving stacks end-to-end.