Metraipolis › archive › dc_36749fd3cd01

Identifying Intelligent Processes via Online Sequential Testing — arXiv:2609.26193

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26193
License (as archived): CC0-1.0
Archived: 2026-10-08T13:45:38.933Z
SHA-256 of the archived text: 9d1b607140686cb09c2a772279f9fef3af54bc0e394002ccc05706db200f985e
Stable URL of this page: https://metraipolis.com/documento/dc_36749fd3cd01

How to cite

Identifying Intelligent Processes via Online Sequential Testing — arXiv:2609.26193 — arXiv (en), https://arxiv.org/abs/2609.26193 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_36749fd3cd01 (Metraipolis archive dc_36749fd3cd01, sha256 9d1b607140686cb09c2a772279f9fef3af54bc0e394002ccc05706db200f985e)

BibTeX

@misc{dc36749fd3cd01,
  title = {Identifying Intelligent Processes via Online Sequential Testing — arXiv:2609.26193},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26193},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_36749fd3cd01; sha256 9d1b607140686cb09c2a772279f9fef3af54bc0e394002ccc05706db200f985e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26193. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Active sequential hypothesis testing studies how to identify an unknown hypothesis with a given set of sensing actions. We study this in the setting of identifying large language models (LLMs), \textit{i.e.}, if a user is conversing with an LLM drawn from a known set of models, how can they identify which one is in use? Here, the available sensing actions (evaluations) are themselves a design choice: an evaluator must first decide which environments and prompt families to construct, and only then decide how to use them sequentially. We formalize these two levels as an outer probe-design problem and an inner identification problem. Simply put, the outer stage selects a set of probes to be sent to the entire set of models, creating a kind of fingerprint dataset. This is followed by the inner stage, which sequentially sends a budget-minimizing set of those probes to identify the model in use. For the outer problem, we show that selecting which evaluations to construct at minimum cost, so that every pair of candidates is distinguished, is exactly a weighted set cover problem. Since the response distributions of the candidate models are not known exactly but only through calibration samples, we give a one-shot procedure that estimates the cover instance from these samples. For the inner problem, we bound the number of evaluations needed to identify the unknown model in terms of how well the available evaluations distinguish each pair of candidates.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.26193 — 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 2026-10-08T13:18:38.157Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).