AI Paper Atlas

Research map / Large language models / Reasoning and chain of thought

Best-of-Infinity: Asymptotic Performance of Test-Time Compute

Junpei Komiyama, Daisuke Oba, Masafumi Oyamada

ICLR 2026 · Large language models › Reasoning and chain of thought · approach: Test-time compute scaling

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies best-of-N with majority-vote selection in the limit N→∞ (best-of-∞) and proposes an adaptive generation scheme that chooses N based on answer agreement to approach that limit efficiently.

Problem

Best-of-N test-time scaling with majority-vote selection requires an effectively infinite test-time budget to reach its asymptotic performance.

Approach

Analyzes the N→∞ limit of majority-vote best-of-N (best-of-∞) and proposes adaptively choosing N according to answer agreement among sampled responses, so generation stops once the vote is stable.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use adaptive Bayes-factor sampling instead of fixed N in majority votingGPT-OSS-20B majority voting · MATH500accuracy vs samples: average N=3 matches fixed N=10; average N≈10 matches fixed N=100Improved
use MILP-weighted ensemble of multiple LLMs instead of the best single LLMbest-of-infinity majority voting · AIME2025best-of-infinity accuracy: 90.0 -> 93.3Improved
ensemble of five LLMs with optimized weights instead of any single LLMmajority voting · GPQA-DiamondaccuracyImproved
learn ensemble weights from AIME2024 and apply to AIME2025three-model ensembles · AIME2025 (transfer)matches or exceeds best single model: 106 of 165 combinations (64.2%)Mixed
select answer by majority voting instead of reward models or LLM-as-a-judgeGPT-OSS-20B Bo5 · AIME2025accuracy: 85.42 vs 82.92 (judge), 80.00 (best reward model)Improved
select answer by self-certainty instead of random selectionGPT-OSS-20B Bo5 · AIME2025accuracy: 76.25 -> 75.83No clear effect
use more samples N in majority voting (ablation)GPT-OSS-20B · four reasoning benchmarksaccuracyImproved
learn weights from only five training problems (ablation)ensemble weight MILP · AIME2025best-of-infinity accuracyImproved

Experimental setup

Builds on: best-of-n sampling self-consistency

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy