Metraipolis › archive › dc_bb8e154aaf32
ServerBench: How can your coding agents design specialized LLM serving systems? — arXiv:2611.06841
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06841
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:17:12.334Z
- SHA-256 of the archived text
b2f1030f6dd163e5ca78c3a1632812f81065823822e921958ce001b099d82cb0- Stable URL of this page
https://metraipolis.com/documento/dc_bb8e154aaf32
How to cite
ServerBench: How can your coding agents design specialized LLM serving systems? — arXiv:2611.06841 — arXiv (en), https://arxiv.org/abs/2611.06841 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb8e154aaf32 (Metraipolis archive dc_bb8e154aaf32, sha256 b2f1030f6dd163e5ca78c3a1632812f81065823822e921958ce001b099d82cb0)
BibTeX
@misc{dcbb8e154aaf32,
title = {ServerBench: How can your coding agents design specialized LLM serving systems? — arXiv:2611.06841},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06841},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb8e154aaf32; sha256 b2f1030f6dd163e5ca78c3a1632812f81065823822e921958ce001b099d82cb0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06841. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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, $4.87\times$ 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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.06841 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:12:49.018Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).