Cover Image

Every Rollout Counts: Optimal Resource Allocation for Efficient Test-Time Scaling

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Xinglin, Li, Yiwei, Feng, Shaoxiong, Yuan, Peiwen, Zhang, Yueqi, Shi, Jiayi, Tan, Chuyi, Pan, Boyuan, Hu, Yao, Li, Kan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling
by: Wang, Xinglin, et al.
Published: (2026)

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
by: Wang, Xinglin, et al.
Published: (2024)

On Time, Within Budget: Constraint-Driven Online Resource Allocation for Agentic Workflows
by: Wang, Xinglin, et al.
Published: (2026)

LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient
by: Yuan, Peiwen, et al.
Published: (2025)

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation
by: Yuan, Peiwen, et al.
Published: (2025)

UniCBE: An Uniformity-driven Comparing Based Evaluation Framework with Unified Multi-Objective Optimization
by: Yuan, Peiwen, et al.
Published: (2025)

Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator
by: Yuan, Peiwen, et al.
Published: (2025)

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
by: Zhang, Yueqi, et al.
Published: (2025)

From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MARKERGEN
by: Yuan, Peiwen, et al.
Published: (2025)

InsBank: Evolving Instruction Subset for Ongoing Alignment
by: Shi, Jiayi, et al.
Published: (2025)

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
by: Li, Yiwei, et al.
Published: (2025)

Diagnosing and Mitigating System Bias in Self-Rewarding RL
by: Tan, Chuyi, et al.
Published: (2025)

PatternKV: Flattening KV Representation Expands Quantization Headroom
by: Zhang, Ji, et al.
Published: (2025)

Speculative Decoding for Multi-Sample Inference
by: Li, Yiwei, et al.
Published: (2025)

Focused Large Language Models are Stable Many-Shot Learners
by: Yuan, Peiwen, et al.
Published: (2024)

Learning More from Less: Unlocking Internal Representations for Benchmark Compression
by: Zhang, Yueqi, et al.
Published: (2026)

Instruction Embedding: Latent Representations of Instructions Towards Task Identification
by: Li, Yiwei, et al.
Published: (2024)

BatchEval: Towards Human-like Text Evaluation
by: Yuan, Peiwen, et al.
Published: (2023)

CogLM: Tracking Cognitive Development of Large Language Models
by: Wang, Xinglin, et al.
Published: (2024)

Poor-Supervised Evaluation for SuperLLM via Mutual Consistency
by: Yuan, Peiwen, et al.
Published: (2024)

Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation
by: Wang, Xinglin, et al.
Published: (2024)

Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
by: Li, Yiwei, et al.
Published: (2024)

Generative Dense Retrieval: Memory Can Be a Burden
by: Yuan, Peiwen, et al.
Published: (2024)

OptPO: Optimal Rollout Allocation for Test-time Policy Optimization
by: Wang, Youkang, et al.
Published: (2025)

Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR
by: Wang, Tao, et al.
Published: (2026)

Test-Time Scaling of Reasoning Models for Machine Translation
by: Li, Zihao, et al.
Published: (2025)

Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding
by: Yin, Hang, et al.
Published: (2025)

When Every Token Counts: Optimal Segmentation for Low-Resource Language Models
by: Raj, Bharath, et al.
Published: (2024)

How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
by: Fang, Yangyi, et al.
Published: (2026)

SCALE: Selective Resource Allocation for Overcoming Performance Bottlenecks in Mathematical Test-time Scaling
by: Xiao, Yang, et al.
Published: (2025)

Balancing Fairness and Efficiency in Energy Resource Allocations
by: Li, Jiayi, et al.
Published: (2024)

A Rollout-Based Algorithm and Reward Function for Resource Allocation in Business Processes
by: Middelhuis, Jeroen, et al.
Published: (2025)

Making Every Bit Count for $A$-Optimal State Estimation
by: Khanpour, Cameron, et al.
Published: (2026)

Efficient Test-Time Scaling via Temporal Reasoning Aggregation
by: Li, Jiakun, et al.
Published: (2026)

Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation
by: Li, Yiwei, et al.
Published: (2024)

Count Every Rotation and Every Rotation Counts: Exploring Drone Dynamics via Propeller Sensing
by: Chen, Xuecheng, et al.
Published: (2025)

Video-T1: Test-Time Scaling for Video Generation
by: Liu, Fangfu, et al.
Published: (2025)

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs
by: Ling Team, et al.
Published: (2025)

Precision Photochemistry: Every Photon Counts
by: Fred Pashley‐Johnson, et al.
Published: (2025)

SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout
by: Jiang, Chiyu Max, et al.
Published: (2024)