Metraipolis › archive › dc_931faa5e62df

Uncertainty-Aware Budget Allocation for Efficient LLM Tree Search — arXiv:2610.22858

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22858
License (as archived)
CC0-1.0
Archived
2026-10-19T08:43:01.049Z
SHA-256 of the archived text
04bbdd70401312d51cb85e81285fb2f66974e3a07f5cb9450d1242405f8f1817
Stable URL of this page
https://metraipolis.com/documento/dc_931faa5e62df

How to cite

Uncertainty-Aware Budget Allocation for Efficient LLM Tree Search — arXiv:2610.22858 — arXiv (en), https://arxiv.org/abs/2610.22858 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_931faa5e62df (Metraipolis archive dc_931faa5e62df, sha256 04bbdd70401312d51cb85e81285fb2f66974e3a07f5cb9450d1242405f8f1817)
BibTeX
@misc{dc931faa5e62df,
  title = {Uncertainty-Aware Budget Allocation for Efficient LLM Tree Search — arXiv:2610.22858},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22858},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_931faa5e62df; sha256 04bbdd70401312d51cb85e81285fb2f66974e3a07f5cb9450d1242405f8f1817},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22858. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tree search enhances multi-step reasoning in large language models (LLMs), yet prevailing methods expand every step with a fixed budget, irrespective of the marginal utility of expansion. We first show, across existing search algorithms, that continuations sampled from a shared intermediate state are largely duplicates and collapse to a few distinct answers. Critically, we find that the semantic dispersion of sibling actions predicts the redundancy of their downstream continuations, permitting a subtree's budget to be fixed before expansion. An information-theoretic analysis motivates this: treating the per-step budget as the Monte Carlo sample size for estimating a step's residual answer entropy, we derive a sufficient budget that shrinks with sibling dispersion. We accordingly propose $\textbf{Uncertainty-Aware Allocation}$ (UAA), a training-free framework that decouples value from uncertainty: values determine which candidates are promising, while uncertainty, estimated from sibling dispersion at no additional model cost, determines how many merit expansion, via uncertainty-aware pruning and uncertainty-aware budgeting. Across mathematical reasoning, logical reasoning, and planning benchmarks, UAA reduces token usage by up to $90\%$ and latency by up to $9\times$ at comparable accuracy, generalizing across four tree search algorithms and both open- and closed-source LLMs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.22858 — 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 2026-10-19T08:39:10.129Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).