Metraipolis › archive › dc_bc45ba561900

When does a scaling result justify a different allocation? A critical review of resource-allocation evidence for AI systems — arXiv:2609.14500

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.14500
License (as archived): CC0-1.0
Archived: 2026-10-15T22:47:30.817Z
SHA-256 of the archived text: ff63dbf3f689fdaf4612ef3ceca43c38351b60a959f0712629f2fea2b5a0142b
Stable URL of this page: https://metraipolis.com/documento/dc_bc45ba561900

How to cite

When does a scaling result justify a different allocation? A critical review of resource-allocation evidence for AI systems — arXiv:2609.14500 — arXiv (en), https://arxiv.org/abs/2609.14500 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc45ba561900 (Metraipolis archive dc_bc45ba561900, sha256 ff63dbf3f689fdaf4612ef3ceca43c38351b60a959f0712629f2fea2b5a0142b)

BibTeX

@misc{dcbc45ba561900,
  title = {When does a scaling result justify a different allocation? A critical review of resource-allocation evidence for AI systems — arXiv:2609.14500},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14500},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc45ba561900; sha256 ff63dbf3f689fdaf4612ef3ceca43c38351b60a959f0712629f2fea2b5a0142b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14500. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI scaling studies increasingly evaluate systems that combine a pretrained model with retrieval, search, verification, tools, and interaction. Yet a higher score under a larger budget does not by itself show where additional resources are best spent. This critical integrative review asks when a reported scaling result supports a resource-allocation decision. It compares evidence across pretraining, test-time computation, retrieval, and agent evaluation, distinguishing the performance of a tested procedure from the best performance achievable under a resource limit. The synthesis shows that three mismatches recur across this evidence: success counted before an answer is chosen, information a deployed system will not have, and costs left out of the comparison. A capability surface expresses performance as a function of budgets, mechanisms, and available information. Worked analytical examples show how the evaluation metric, deployment volume, selection rule, and stopping policy can alter an allocation conclusion. A resource envelope provides a structured record of the task, development and run-time resources, information access, and procedure behind a reported score. Its application to a published comparison illustrates which conclusions the evidence supports and which deployment questions remain unresolved. The resulting framework specifies the comparisons needed to choose among feasible systems and motivates experiments on the transfer of allocation rules across tasks and operating conditions. It does not propose a universal scaling law or infer general intelligence from benchmark gains.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.14500 — 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 2026-10-15T22:29:03.185Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).