cs.AINov 4, 2026

ServerBench: How can your coding agents design specialized LLM serving systems?

Authors: Xinrui Zhong, Zhiming Wang, Yongqi Liu, Zhaohui Wang, Shanglin Yang, Zikun Li, Zhuoming Chen, Beidi Chen

Organizations: Carnegie Mellon University · University of Southern California

Abstract

Large language model (LLM) coding agents develop software through experimentation, offering an opportunity to design the serving systems supporting their own operation. Effective serving requires coordinating implementation and operating decisions under session dependencies, latency constraints, and correctness requirements. We introduce ServerBench, a benchmark for agentic design of complete, specialized LLM serving systems. Agents experiment against a common objective, dollars per dollar: latency-qualified token value per dollar of GPU cost. Stateful replay preserves session dependencies, and independent verification checks the submitted system. Across 11 coding-agent models and three deployments, Claude Sonnet 5.5 achieves 2.97 dollars per dollar on Gemma E4B, 4.87×4.87\times the vLLM reference; 22 of 33 runs yield verified systems, and 13 exceed the strongest baseline. Our analysis identifies three findings: high-value designs coordinate capacity improvements with load selection; agents interpret performance feedback through workload-relevant experiments; and reliable delivery requires verification of the execution paths introduced by optimization. Overall, ServerBench supports systematic study of how agents translate service objectives and feedback into effective, verified serving systems for given task specifications.

Figures & tables

Explore similar work

CardsList
  1. VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?

    May 7, 2026Keisuke Kamahori, Shihang Li, Simon Peter +1Multi-Agent LLM SystemsLLM Serving

  2. TraceLab: Characterizing Coding Agent Workloads for LLM Serving

    Jun 29, 2026Kan Zhu, Mathew Jacob, Chenxi Ma +4LLM ServingAI Coding Agents