Metraipolis › archive › dc_ab7336c482cd

Test-Time Scaling via Budgeted Multi-Attribute Verification — arXiv:2609.34322

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34322
License (as archived)
CC0-1.0
Archived
2026-10-07T20:57:39.798Z
SHA-256 of the archived text
b384d580bbc5ea7b395e2d368877d2c5a4c69e24d011368dca727a24878fc5a4
Stable URL of this page
https://metraipolis.com/documento/dc_ab7336c482cd

How to cite

Test-Time Scaling via Budgeted Multi-Attribute Verification — arXiv:2609.34322 — arXiv (en), https://arxiv.org/abs/2609.34322 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab7336c482cd (Metraipolis archive dc_ab7336c482cd, sha256 b384d580bbc5ea7b395e2d368877d2c5a4c69e24d011368dca727a24878fc5a4)
BibTeX
@misc{dcab7336c482cd,
  title = {Test-Time Scaling via Budgeted Multi-Attribute Verification — arXiv:2609.34322},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34322},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab7336c482cd; sha256 b384d580bbc5ea7b395e2d368877d2c5a4c69e24d011368dca727a24878fc5a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34322. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Verifying LLM-generated answers under a shared computational budget requires jointly deciding which candidates to inspect and which verification attributes to evaluate. We formulate this problem as multi-attribute good-arm identification under a global budget: each candidate is an arm evaluated along several costly attributes, and the goal is to certify as many candidates as possible whose mean scores exceed the prescribed thresholds on all attributes. We propose \textsc{BMA-GAI}, an algorithm that combines cost-aware arm selection with adaptive sampling of attributes. Every observation serves both to guide adaptive allocation and to support anytime-valid certification, which removes the need for a separate confirmation stage. We establish an asymptotic coverage guarantee for \textsc{BMA-GAI} and derive a matching information-theoretic converse that characterizes the intrinsic complexity of the problem, thereby proving that \textsc{BMA-GAI} is first-order optimal away from critical budget levels. Experiments on synthetic benchmarks and an LLM answer-verification task show that \textsc{BMA-GAI} allocates the verification budget more efficiently and certifies more high-quality candidates than competing methods.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34322 — 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 2026-10-07T20:29:01.513Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).