Imagen de Portada

RoBoN: Routed Online Best-of-n for Test-Time Scaling with Multiple LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Geuter, Jonathan, Kornhardt, Gregor
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CarBoN: Calibrated Best-of-N Sampling Improves Test-time Reasoning
por: Tang, Yung-Chen, et al.
Publicado: (2025)

AdaBoN: Adaptive Best-of-N Alignment
por: Raman, Vinod, et al.
Publicado: (2025)

Universal Neural Optimal Transport
por: Geuter, Jonathan, et al.
Publicado: (2022)

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
por: Qiu, Jiahao, et al.
Publicado: (2024)

Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
por: Huang, Audrey, et al.
Publicado: (2025)

BoTTA: Benchmarking on-device Test Time Adaptation
por: Danilowski, Michal, et al.
Publicado: (2025)

BoSS: A Best-of-Strategies Selector as an Oracle for Deep Active Learning
por: Huseljic, Denis, et al.
Publicado: (2026)

Near-Optimal Online Deployment and Routing for Streaming LLMs
por: Li, Shaoang, et al.
Publicado: (2025)

Guided Speculative Inference for Efficient Test-Time Alignment of LLMs
por: Geuter, Jonathan, et al.
Publicado: (2025)

A Regret Perspective on Online Multiple Testing
por: Hao, Qingyang, et al.
Publicado: (2026)

Best-of-$\infty$ -- Asymptotic Performance of Test-Time LLM Ensembling
por: Komiyama, Junpei, et al.
Publicado: (2025)

BOND: Aligning LLMs with Best-of-N Distillation
por: Sessa, Pier Giuseppe, et al.
Publicado: (2024)

Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts
por: Lee, Jihoon, et al.
Publicado: (2025)

Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing
por: Zhang, Zeyu, et al.
Publicado: (2026)

Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment
por: Sriraman, Ved, et al.
Publicado: (2026)

RoS-Guard: Robust and Scalable Online Change Detection with Delay-Optimal Guarantees
por: Zhu, Zelin, et al.
Publicado: (2025)

When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs
por: Wang, Keyu, et al.
Publicado: (2025)

S*: Test Time Scaling for Code Generation
por: Li, Dacheng, et al.
Publicado: (2025)

T-POP: Test-Time Personalization with Online Preference Feedback
por: Qu, Zikun, et al.
Publicado: (2025)

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
por: Xu, Zhiyuan, et al.
Publicado: (2026)

Constrained Best Arm Identification with Tests for Feasibility
por: Cai, Ting, et al.
Publicado: (2025)

Rethinking RoPE: A Mathematical Blueprint for N-dimensional Positional Embedding
por: Liu, Haiping, et al.
Publicado: (2025)

BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute
por: Ding, Dujian, et al.
Publicado: (2025)

Test-Time Training on Graphs with Large Language Models (LLMs)
por: Zhang, Jiaxin, et al.
Publicado: (2024)

Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
por: Hübotter, Jonas, et al.
Publicado: (2024)

Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
por: Miyamoto, Sora, et al.
Publicado: (2026)

Understanding the Role of Training Data in Test-Time Scaling
por: Javanmard, Adel, et al.
Publicado: (2025)

Q-ROAR: Outlier-Aware Rescaling for RoPE Position Interpolation in Quantized Long-Context LLMs
por: Qiao, Ye, et al.
Publicado: (2025)

Best-of-N Jailbreaking
por: Hughes, John, et al.
Publicado: (2024)

Rethinking RoPE Scaling in Quantized LLM: Theory, Outlier, and Channel-Band Analysis with Weight Rescaling
por: Qiao, Ye, et al.
Publicado: (2025)

Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling
por: Tran, Dao, et al.
Publicado: (2026)

RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Data
por: Mou, Xudong, et al.
Publicado: (2025)

Best of mini-N in-loop Sampling: A Contextual Quality Reward Model for Reliable and Efficient Best-of-N Sampling
por: Rho, Hyung Gyu, et al.
Publicado: (2025)

Variational Best-of-N Alignment
por: Amini, Afra, et al.
Publicado: (2024)

RouteLLM: Learning to Route LLMs with Preference Data
por: Ong, Isaac, et al.
Publicado: (2024)

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
por: Chen, Hao Mark, et al.
Publicado: (2025)

Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
por: Shen, Junhong, et al.
Publicado: (2025)

Effective Test-Time Scaling of Discrete Diffusion through Iterative Refinement
por: Lee, Sanghyun, et al.
Publicado: (2025)

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models
por: Bilal, Ahsan, et al.
Publicado: (2026)

Lookahead Sample Reward Guidance for Test-Time Scaling of Diffusion Models
por: Kim, Yeongmin, et al.
Publicado: (2026)