Metraipolis › archive › dc_6870fc7daf73
RADE: Risk-Adjusted Deployment Efficiency, A Framework for Routing, Memory, and Escalation in Safe LLM Systems — arXiv:2611.11659
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.11659
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:41:28.887Z
- SHA-256 of the archived text
ae1f3e9a080305ebd24c77dcb7b3045985db518b710b49d621fde9cbdc9ce4f8- Stable URL of this page
https://metraipolis.com/documento/dc_6870fc7daf73
How to cite
RADE: Risk-Adjusted Deployment Efficiency, A Framework for Routing, Memory, and Escalation in Safe LLM Systems — arXiv:2611.11659 — arXiv (en), https://arxiv.org/abs/2611.11659 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6870fc7daf73 (Metraipolis archive dc_6870fc7daf73, sha256 ae1f3e9a080305ebd24c77dcb7b3045985db518b710b49d621fde9cbdc9ce4f8)
BibTeX
@misc{dc6870fc7daf73,
title = {RADE: Risk-Adjusted Deployment Efficiency, A Framework for Routing, Memory, and Escalation in Safe LLM Systems — arXiv:2611.11659},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.11659},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6870fc7daf73; sha256 ae1f3e9a080305ebd24c77dcb7b3045985db518b710b49d621fde9cbdc9ce4f8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.11659. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A deployed language model does not merely answer questions. It spends computation, consumes time, consults evidence, exposes memory, invites or avoids human review, and sometimes makes mistakes whose consequences are radically unequal. Yet LLM systems are still commonly compared as if the relevant object were a single model and the relevant outcome were a single benchmark score. This paper argues that the unit of analysis should instead be the deployment policy: the mechanism that decides when to retrieve, when to remember, when to call a larger model, when to verify, and when not to answer at all. We introduce risk-adjusted deployment efficiency (RADE), a system-level objective that scores the utility a deployment delivers net of inference, retry, oversight, and priced expected failure cost, while treating harms that cannot be priced as hard budgets alongside constraints on latency, privacy, and resources. The framework brings selective routing, retrieval and governed memory, efficient specialization, uncertainty estimation, abstention, and human escalation into a common account. We then examine five deployment regimes in which the same nominal LLM capability leads to different rational architectures, and propose a reporting protocol based on risk-coverage behavior, end-to-end cost, update drift, memory exposure, evidence quality, and escalation load. The central claim is modest but consequential: frontier capability should be treated as a resource to allocate, not a default state to maintain. A safe and sustainable system is not the one that always uses the strongest model; it is the one that spends capability where the reduction in risk or increase in utility justifies the cost. 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/2611.11659 — 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 2026-11-10T18:37:37.518Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).