The paper investigates how AI systems that perform best‑of‑n search require different validation strategies as the search width changes. It shows that auditing only small search widths leaves a gap in reliability estimates for larger widths, and proposes retaining candidate ranks and truth labels to estimate reliability across all widths up to N. The authors derive theoretical bounds on the minimax mean‑squared error, design procedures that achieve these bounds, and demonstrate that a shared audit can significantly reduce maximum error across many widths in practical CodeRM pools.
By Ricardo Fitas
arXiv:2606. 19354v1 Announce Type: cross Abstract: Test-time scaling (TTS) has emerged as a powerful paradigm for improving the reasoning performance of large language models (LLMs) by investing additional compute at inference time.
By Ardit Krasniqi, Luan Vejsiu, Elira Dervishi
The paper introduces OMVV, an online multi-verifier algorithm that maintains a pool of weak verifiers with varying costs and performance. It adaptively selects a verifier each round using an online score combiner and exponential-weights routing, providing distribution-free guarantees on false-accept and false-reject rates. Experiments on reasoning benchmarks show OMVV achieves higher accuracy at lower verification cost than any single fixed verifier across different budgets.
By Erfan Hajihashemi, Yanning Shen
arXiv:2607. 11635v1 Announce Type: new Abstract: In fixed-budget best-arm identification, also known as ranking and selection, an algorithm has a sampling budget to distribute across $K$ arms.
By Motti Goldberger
arXiv:2610.16840v1 Announce Type: cross
Abstract: Real-world systems often serve many objectives but can deploy only a few options, whose performance must be learned from noisy feedback. Modeling eac...
By Bo Xue, Yilu Liu, Haodong Jing, Hongzong Li, Xi Lin, Shuang Qiu
arXiv:2607. 20950v1 Announce Type: new Abstract: BoN improves model outputs by sampling several candidates and selecting one with a proxy score, but it assumes that complete candidates can be evaluated reliably.
By Cenwei Zhang, Teng Fang, Yuxia Wang, Derek Li, Bryan Dai, Lei You
arXiv:2610.14996v1 Announce Type: new
Abstract: Choosing a few robust algorithms or schedules can require evaluating every candidate under many adverse scenarios, even though an agent only needs to i...
By Yuhe Sui, Yingzhi Tang
BoN improves model outputs by sampling several candidates and selecting one with a proxy score, but it assumes that complete candidates can be evaluated reliably. Many vision-language tasks instead provide only partial verification: a finding, span, value, region, or relation may be checkable even when no dependable whole-response verifier exists.
The paper introduces Uncertainty-Aware Budget Allocation (UAB), a concave integer optimization framework that reallocates a fixed sampling budget for language model reasoning based on uncertainty estimated from initial samples. In Phase‑1, each question receives a small number of generations, and the disagreement among these answers (vote entropy) signals difficulty. Phase‑2 uses a marginal‑greedy algorithm to allocate the remaining budget, focusing on questions with high initial disagreement, leading to a 2.3% average accuracy improvement over uniform allocation across five open‑weight models and five reasoning benchmarks, with up to 5.5% gains on individual benchmarks, especially in low‑resource settings.
By Manh Nguyen, Sunil Gupta, Hung Le
arXiv:2609.37493v1 Announce Type: cross
Abstract: Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error...
By Dongyub Jude Lee, Jungseob Lee, Chanjun Park, Hyeonseok Moon, Heuiseok Lim
The paper introduces a new variant of the multi‑armed bandit problem that incorporates dueling feedback—pairwise comparisons of model responses—and heterogeneous sampling costs to identify the best large language model (LLM) from a set with varying query costs. Assuming a Condorcet winner, the authors propose a Track‑and‑Stop style algorithm that guarantees asymptotically optimal cost as the error probability approaches zero. Extensive experiments on synthetic and real‑world data show that this cost‑aware approach consistently outperforms both classical cost‑unaware algorithms and other cost‑aware extensions.
By Sarvesh Gharat, Nikhil Karamchandani, Jayakrishnan Nair
Test-time scaling can improve LLM reasoning, but existing approaches typically adapt generation or apply answer selection after a predetermined generation schedule. We study within-instance allocation...