Metraipolis › archive › dc_a3d09ac6b4fc

Retaining Repair Hypotheses for Cost-Aware Execution — arXiv:2610.39410

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39410
License (as archived)
CC0-1.0
Archived
2026-10-31T06:09:17.335Z
SHA-256 of the archived text
331e48c13eea869f4898e545e77bef4f284a5ad6509df44cf70df12bca169f04
Stable URL of this page
https://metraipolis.com/documento/dc_a3d09ac6b4fc

How to cite

Retaining Repair Hypotheses for Cost-Aware Execution — arXiv:2610.39410 — arXiv (en), https://arxiv.org/abs/2610.39410 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3d09ac6b4fc (Metraipolis archive dc_a3d09ac6b4fc, sha256 331e48c13eea869f4898e545e77bef4f284a5ad6509df44cf70df12bca169f04)
BibTeX
@misc{dca3d09ac6b4fc,
  title = {Retaining Repair Hypotheses for Cost-Aware Execution — arXiv:2610.39410},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39410},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3d09ac6b4fc; sha256 331e48c13eea869f4898e545e77bef4f284a5ad6509df44cf70df12bca169f04},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39410. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Several corrections of an executable model can fit the same observations while predicting different execution outcomes. We study a repair-to-execution interface that retains compatible finite guard repairs, conditions their weights on diagnostic and ordinary-execution observations, and uses their predictions to choose routes, priced tests, or a backup. On 24 synthetic two-stage devices, an equal mixture of a language-model-generated repair and a uniform belief over compatible repairs (the AI-weighted belief) lowers no-test cost by 2.14 percent relative to committing to the generated repair. Access charges can erase the benefit of diagnosis on isolated tasks, while repeated work can recover it under the AI-weighted belief. With normal-execution learning in every repeated-work arm, workload-valued testing costs 3.33 percent less than same-budget random selection under the AI-weighted belief. Weighting changes the comparison: uniform normal learning costs 540.75 less than AI-weighted normal learning on this cohort, with a device-paired interval excluding zero. Testing recovers part of that gap, but uniform normal learning still has a lower aggregate cost than AI-weighted workload-valued selection. Under uniform beliefs, information-gain selection has the lowest total among the compared selectors, while workload-valued testing costs more than normal learning. These results support retaining alternatives to a generated repair and evaluating diagnostic selection together with repair weighting and learning from execution.

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/2610.39410 — 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 2026-10-31T06:07:08.519Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).