Metraipolis › archive › dc_c9b00a4d9cde

DIMWIT: Directly Invoking Models Without Intensive Tuning — arXiv:2611.01463

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01463
License (as archived): CC0-1.0
Archived: 2026-11-03T10:56:39.125Z
SHA-256 of the archived text: 5cb0f5133f90b75581a4b6342239a24deda259e299edb3643dd49d880909470e
Stable URL of this page: https://metraipolis.com/documento/dc_c9b00a4d9cde

How to cite

DIMWIT: Directly Invoking Models Without Intensive Tuning — arXiv:2611.01463 — arXiv (en), https://arxiv.org/abs/2611.01463 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c9b00a4d9cde (Metraipolis archive dc_c9b00a4d9cde, sha256 5cb0f5133f90b75581a4b6342239a24deda259e299edb3643dd49d880909470e)

BibTeX

@misc{dcc9b00a4d9cde,
  title = {DIMWIT: Directly Invoking Models Without Intensive Tuning — arXiv:2611.01463},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01463},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c9b00a4d9cde; sha256 5cb0f5133f90b75581a4b6342239a24deda259e299edb3643dd49d880909470e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01463. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Resource managers typically encode what to do in a task-specific policy---a heuristic, an optimization procedure, or a model trained for the task---that must be developed before use and may need revision as the workload or system changes. We propose bypassing policy development and instead asking pretrained models to make resource-management decisions directly, given the current system state, desired outcome, and available choices. We evaluate this approach on microservice autoscaling, DRAM sizing, and video encoding, using a frontier LLM and two small decision models. On two microservice applications, a small decision model meets latency targets while using within 10% of the replicas allocated by policy-based autoscalers and within 13% of the frontier LLM. In DRAM sizing, a small decision model reduces DRAM usage by up to 27.5% relative to static provisioning while maintaining at least 95% of baseline performance. In video encoding, it completes encodes up to 4.3$\times$ faster than the frontier LLM, with an imperceptible 1.1-point decrease in Video Multi-Method Assessment Fusion (VMAF), a metric of perceptual video quality. Making individual resource-management decisions may be considerably simpler than developing a general strategy for making them.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Performance (cs.PF) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Distributed, Parallel, and Cluster Computing (cs.DC); Operating Systems (cs.OS).
Pagina del lavoro: https://arxiv.org/abs/2611.01463 — 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 2026-11-03T10:49:38.554Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).