Simthesizer: An Agent-Driven Simulation Framework for LLM Serving Systems

2026-08-25

AI Summary

为解决现有模拟器无法跟上LLM服务系统快速演进的问题，本文提出Simthesizer框架，通过代理驱动的开发方法实现更高效、准确的系统级模拟。

Abstract

System-level simulation is an essential tool for exploring the rapidly expanding design space of LLM serving systems, where real deployments remain costly and often infeasible. However, modern LLM serving now evolves faster than human-driven simulator development can track, and emerging workloads and mechanisms, from agentic workflows to disaggregated serving, no longer fit the monolithic simulation pipeline that existing simulators assume. Each new mechanism therefore demands an invasive rewrite, leaving a widening development gap between deployed serving systems and the simulators that model them. To close this gap, we present Borg, a framework that realizes agent-driven simulator development. Borg introduces a composable simulator infrastructure that uniformly expresses the complete serving workflow, including the control decisions that coordinate it, and realizes it as a unified dynamic graph in Borg simulator. Synthesizer agent, a harnessed coding agent, then lowers natural-language feature requests onto this abstraction under simulator-specific guardrails and fidelity validation, evolving one shared simulator instead of building a new one for every feature. Under the same coding agent and harnesses, extensions built on Borg follow a vLLM-based real system with 2.51% average throughput error, versus 6.03% for extensions built on existing simulators. On identical workloads, Borg also simulates up to 284.96x and 23.19x faster than two state-of-the-art simulators, LLMServingSim2.0 and Vidur, respectively.

Problem

• LLM serving systems
• simulation framework
• agent-driven development
• emerging workloads
• development gap

Innovation

• agent-driven simulation
• composable simulator infrastructure
• dynamic graph
• natural-language feature requests
• synthesizer agent