Metraipolis › archive › dc_cae4f2fac750
Bridging Agent Semantics with Spot Capacity: An Elastic and Recoverable Service Model — arXiv:2608.29581
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29581
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:19:01.971Z
- SHA-256 of the archived text
1d66f1f099284a74454c2d3cacf662c25d690ef67b366b34ead765370973f1b8- Stable URL of this page
https://metraipolis.com/documento/dc_cae4f2fac750
How to cite
Bridging Agent Semantics with Spot Capacity: An Elastic and Recoverable Service Model — arXiv:2608.29581 — arXiv (en), https://arxiv.org/abs/2608.29581 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cae4f2fac750 (Metraipolis archive dc_cae4f2fac750, sha256 1d66f1f099284a74454c2d3cacf662c25d690ef67b366b34ead765370973f1b8)
BibTeX
@misc{dccae4f2fac750,
title = {Bridging Agent Semantics with Spot Capacity: An Elastic and Recoverable Service Model — arXiv:2608.29581},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29581},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cae4f2fac750; sha256 1d66f1f099284a74454c2d3cacf662c25d690ef67b366b34ead765370973f1b8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29581. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLM agents increasingly drive long-running cloud inference workloads in which model calls differ in urgency, redundancy, completion semantics, and replay cost. Model-as-a-Service (MaaS) platforms expose several service models for trading cost against latency, availability, and capacity commitment. These models operate primarily at request, job, or endpoint scopes and provide limited support for combining transient platform supply with the evolving semantics of an agent task. We present SemSpot, a semantics-aware service model that allows agent applications to leverage the spot capacity of LLM inference platforms. At the request level, SemSpot lets a provider publish short-lived offers over successful price, completion probability, and failure-notification deadline; the agent runtime selects among these offers using the current task state and completion rule. An audit of 1,535 cases from six agent benchmarks identifies four recurring workflow structures and shows how this service model may produce different cost, service-time, and fallback behavior. With specialized MaaS support, token-level SemSpot further preserves provider inference state and runtime-verified semantic segments inside a long request. We develop the service model, economic boundary, and the cross-layer research agenda required to realize SemSpot. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-01 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2608.29581 — 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 2026-10-17T08:07:11.115Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).