Metraipolis › archive › dc_592dc2109685
ToolSched: Resource-Efficient Tool Scheduling for Shared-Host LLM Agents — arXiv:2611.05269
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05269
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T19:08:39.825Z
- SHA-256 of the archived text
a67af9d037ef4643d4eb0047ca164772477ceef70d1e9cf91dbbb1a494d544f3- Stable URL of this page
https://metraipolis.com/documento/dc_592dc2109685
How to cite
ToolSched: Resource-Efficient Tool Scheduling for Shared-Host LLM Agents — arXiv:2611.05269 — arXiv (en), https://arxiv.org/abs/2611.05269 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_592dc2109685 (Metraipolis archive dc_592dc2109685, sha256 a67af9d037ef4643d4eb0047ca164772477ceef70d1e9cf91dbbb1a494d544f3)
BibTeX
@misc{dc592dc2109685,
title = {ToolSched: Resource-Efficient Tool Scheduling for Shared-Host LLM Agents — arXiv:2611.05269},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05269},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_592dc2109685; sha256 a67af9d037ef4643d4eb0047ca164772477ceef70d1e9cf91dbbb1a494d544f3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05269. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Local LLM agents often work on shared hosts. Unlike multi-tenant cloud clusters, these hosts often have tightly bounded memory, CPU, and I/O resources. Concurrent agents frequently suffer from resource contention, leading to failures such as OOM and reduced resource efficiency. Considering that agents' resource demands are bursty and shell command delay is imperceptible to agents, there is a huge scheduling opportunity to arrange when and in what order commands are actually executed. Thus, we present ToolSched, a Shell MCP Server for shared local hosts that serves multiple agents and schedules their operations. ToolSched embeds a resource model into the MCP interface: agents estimate resource demands along with command requests. These hints, together with real-time host resource conditions, determine when commands are actually executed. Internally, ToolSched applies a scheduling algorithm to stagger commands, reducing contention and improving resource utilization. Prediction correction and checkpoint-based recovery mitigate estimation bias and resource errors. Our evaluation on Terminal Bench shows that, compared with unscheduled execution, ToolSched improves resource utilization by 148.4% and end-to-end command throughput by 29.4%, demonstrating its effectiveness and practicality. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.OS, nuovi lavori del giorno). Categorie arXiv: Operating Systems (cs.OS). Pagina del lavoro: https://arxiv.org/abs/2611.05269 — 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 2026-11-04T18:42:22.536Z dalla pagina https://arxiv.org/list/cs.OS/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).