Metraipolis › archive › dc_a2a42e07d505

On Turn-Level Best-of-N Sampling for Scaling LLM Agents — arXiv:2611.06868

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.06868
License (as archived): CC0-1.0
Archived: 2026-11-05T18:17:13.239Z
SHA-256 of the archived text: 663b73241e060b7ae9040249d8ab2dfe8ca448fb3fac575dd84315695886d3b2
Stable URL of this page: https://metraipolis.com/documento/dc_a2a42e07d505

How to cite

On Turn-Level Best-of-N Sampling for Scaling LLM Agents — arXiv:2611.06868 — arXiv (en), https://arxiv.org/abs/2611.06868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a2a42e07d505 (Metraipolis archive dc_a2a42e07d505, sha256 663b73241e060b7ae9040249d8ab2dfe8ca448fb3fac575dd84315695886d3b2)

BibTeX

@misc{dca2a42e07d505,
  title = {On Turn-Level Best-of-N Sampling for Scaling LLM Agents — arXiv:2611.06868},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06868},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a2a42e07d505; sha256 663b73241e060b7ae9040249d8ab2dfe8ca448fb3fac575dd84315695886d3b2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this work, we evaluate a simple inference-time scaling approach based on \textit{turn-level best-of-N sampling} (\method) for large language model (LLM) agents on complex, long-horizon tasks. We instantiate this using a \textit{generator-selector} framework with two LLMs; at each turn, a \emph{generator} model generates $N$ candidate actions and a \emph{selector} model selects one of them, which is then executed in the environment. This paper is closely related to the work of \cite{zainullina2025guided} who used critic models for guided search at inference time. Different from their work, we evaluate if off-the-shelf, open-weight LLMs can be effective at comparing different candidate actions directly. Experiments on long-horizon terminal tasks show that \method can lead to significant performance improvements, both in terms of accuracy (5--10\%) and consistency across repeated attempts. Analysis of agent trajectories reveal a shift in agent behaviour towards desirable patterns such as reduction in number of attempts to solve the task, improved task instruction following, debugging and testing.

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/2611.06868 — 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 2026-11-05T18:12:49.019Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).