method · first seen 4 Oct 2026
best-of-N sampling
Also: BoN, Best-of-N, BoN sampling, repeated sampling, best-of-N decoding, multi-sample decoding
Drawing N candidate samples from a generator and returning the one with the highest reward score.
Mentions per week
PapersCodeDiscussion
Rank 169 on 7 Nov 2026 · 14 mentions in 28 days · 14 independent groups · papers · first seen 5 weeks ago · acceleration +1.50
Earliest sources
- Best-of-$N$ Guidance for Test-time Diffusion AlignmentPapers · 4 Oct 2026 · Richard Lee Kim, Yeongmin Kim, Gyuwon Sim, Taekyu Kim, Minsang Park, Il-chul Moo…
- Holdout Best-of-N: Unbiased Evaluation and Its CostPapers · 6 Oct 2026 · Shrey Shah, Yinheng Li
- Efficient Best-of-N policy evaluation for inference-time alignmentPapers · 7 Oct 2026 · Jonas Schweisthal, Yuxin Wang, Athiya Deviyani, Stefan Feuerriegel, Dennis Fraue…
- Non-Prehensile Multi-Object Placement with Mobile Robots via Diffusion-Based Trajectory PlanningPapers · 8 Oct 2026 · Lance Pharand, Megnath Ramesh, Mark Chiu, Yash Vardhan Pant, Stephen L. Smith
- A Critical Look at Power Sampling when Test Time Sharpening LLMsPapers · 9 Oct 2026 · Abiel Malkani Talwar, Christopher Nemeth, Henry Moss
- Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable ProblemsPapers · 14 Oct 2026 · Taro Yano, Yoichi Ishibashi, Masafumi Oyamada
Latest sources
- GRACE: Parallel Best-of-N Multi-Agent Analysis of Closed-Form Questions over Dataframes with Guardrail Selection and Adaptive RetryPapers · 16 Nov 2026 · Fabio Picariello, Salvatore Cipolla, Susanna Bonura, Vito Morreale
- GainCtrl: Predicting Remaining Gains for Efficient LLM Agent ExecutionPapers · 16 Nov 2026 · Kangwen Zhao, Jianfeng Cai, Ruopei Sun, Mingxiao Feng, Peng Zhang, Wengang Zhou,…
- Correct First, Fast Second: What a Local 7B Code Model Can and Cannot Do for GPU Kernel OptimizationPapers · 9 Nov 2026 · Jui-Chien Tsou, Po-Yi Wu
- Aspect-wise Pairwise Tournaments for Test-Time SelectionPapers · 5 Nov 2026 · Hannah Guan, Yilun Du
- Latency-Aware Adaptive Best-of-$N$Papers · 5 Nov 2026 · Alon Jacobson, Qian Xie, Peter I. Frazier
- On Turn-Level Best-of-N Sampling for Scaling LLM AgentsPapers · 4 Nov 2026 · Jalaj Bhandari, Dhawal Gupta, Hongli Zhan, Zhenting Wang, Varad Pimpalkhute, Zhe…
- LAND: Learning an Adaptive Number of Draws for Bayesian Best-of-N SelectionPapers · 2 Nov 2026 · Koen Oostermeijer, Teryn Jones
- Rethinking Neural Decompilation: Candidate Selection as the Hidden BottleneckPapers · 2 Nov 2026 · Felix Mächtle, Gautham Sriram, Manjil Neupane, Nils Loose, Thomas Eisenbarth
- Do Visual RL Gains Scale at Test Time? A Quantile View of Post-TrainingPapers · 2 Nov 2026 · Austin Wang, Lexing Ying
- Selecting or Solving? What Best-of-N Verification Delivers in Video ReasoningPapers · 31 Oct 2026 · Martin Q. Ma, Yuxiao Qu, Ruslan Salakhutdinov, Louis-Philippe Morency, Paden Tom…
- StrictPRMBench: A Replayable Evaluation Benchmark for Auditing Fixed-Score PRM AggregationPapers · 30 Oct 2026 · Pengfei Zheng
- Beyond Passing Tests: A Systematic Review and Controlled Re-evaluation of Techniques for Improving the Quality of LLM-Generated CodePapers · 28 Oct 2026 · Prashank Kadam