Metraipolis › archive › dc_2bb86a37e3f0

Depth or Description? When a One-Step Latent Score Replaces Lookahead in Proactive Information Acquisition — arXiv:2611.07155

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.07155
License (as archived)
CC0-1.0
Archived
2026-11-06T14:42:11.753Z
SHA-256 of the archived text
e3699a3cdd610a836526170ef2153f506e09478bbe207d9b0fd044a32fc8b1ce
Stable URL of this page
https://metraipolis.com/documento/dc_2bb86a37e3f0

How to cite

Depth or Description? When a One-Step Latent Score Replaces Lookahead in Proactive Information Acquisition — arXiv:2611.07155 — arXiv (en), https://arxiv.org/abs/2611.07155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bb86a37e3f0 (Metraipolis archive dc_2bb86a37e3f0, sha256 e3699a3cdd610a836526170ef2153f506e09478bbe207d9b0fd044a32fc8b1ce)
BibTeX
@misc{dc2bb86a37e3f0,
  title = {Depth or Description? When a One-Step Latent Score Replaces Lookahead in Proactive Information Acquisition — arXiv:2611.07155},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.07155},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bb86a37e3f0; sha256 e3699a3cdd610a836526170ef2153f506e09478bbe207d9b0fd044a32fc8b1ce},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.07155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A proactive agent must decide what to ask before it acts. Exact lookahead values combinations of questions but is expensive and leans on a fitted model; a one-step score is cheap but can miss them. Our main finding: the need for depth often lies in how the hidden cause is described. A one-step score on the label can be blind to an interaction among answers. A score on a suitable latent cause is not, and where that latent encodes the decision it replaces most of depth at a fraction of the search. Described differently, the same problem can defeat the score while exact values do not move, so keep the latent small and check it against exact values. Probabilities learned from one language model's answers do not carry to another unless planning allows for both; those read from tokens are worth only a few labels.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.07155 — 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 2026-11-06T14:18:42.667Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).