Imagen de Portada

ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Xiuyu, Zhang, Jinkai, Yi, Mingyang, Li, Yu, Wang, Longqiang, Wang, Yue, Fan, Ju
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers
por: Yang, Zhicheng, et al.
Publicado: (2025)

Echo: Decoupling Inference and Training for Large-Scale RL Alignment on Heterogeneous Swarms
por: Xiao, Jie, et al.
Publicado: (2025)

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

ETS: Efficient Tree Search for Inference-Time Scaling
por: Hooper, Coleman, et al.
Publicado: (2025)

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
por: Wang, Chen, et al.
Publicado: (2025)

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
por: Lin, Weizhe, et al.
Publicado: (2025)

Reveal the Mystery of DPO: The Connection between DPO and RL Algorithms
por: Su, Xuerui, et al.
Publicado: (2025)

JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training
por: Hu, Zhengding, et al.
Publicado: (2026)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
por: Li, Haozhan, et al.
Publicado: (2025)

AdamO: A Collapse-Suppressed Optimizer for Offline RL
por: Qiao, Nan, et al.
Publicado: (2026)

Scaling Test-Time Compute Without Verification or RL is Suboptimal
por: Setlur, Amrith, et al.
Publicado: (2025)

LogoRA: Local-Global Representation Alignment for Robust Time Series Classification
por: Zhang, Huanyu, et al.
Publicado: (2024)

Open-World Test-Time Training: Self-Training with Contrast Learning
por: Su, Houcheng, et al.
Publicado: (2024)

Central Limit Theorem for Two-Time-Scale Approximate Distributionally Robust RL
por: Wang, Shengbo, et al.
Publicado: (2026)

Less is More: Clustered Cross-Covariance Control for Offline RL
por: Qiao, Nan, et al.
Publicado: (2026)

RollArt: Scaling Agentic RL Training via Disaggregated Infrastructure
por: Gao, Wei, et al.
Publicado: (2025)

Dual Alignment Maximin Optimization for Offline Model-based RL
por: Zhou, Chi, et al.
Publicado: (2025)

SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search
por: Li, Dong, et al.
Publicado: (2025)

Towards a Theoretical Understanding to the Generalization of RLHF
por: Li, Zhaochun, et al.
Publicado: (2026)

Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty
por: Wan, Xu, et al.
Publicado: (2026)

Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models
por: Wang, Liangyu, et al.
Publicado: (2025)

Reward-SQL: Boosting Text-to-SQL via Stepwise Reasoning and Process-Supervised Rewards
por: Zhang, Yuxin, et al.
Publicado: (2025)

ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecasting
por: Yuan, Haochen, et al.
Publicado: (2024)

Structural Alignment Improves Graph Test-Time Adaptation
por: Hsu, Hans Hao-Hsun, et al.
Publicado: (2025)

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

On Designing Effective RL Reward at Training Time for LLM Reasoning
por: Gao, Jiaxuan, et al.
Publicado: (2024)

Training-Free Test-Time Adaptation with Brownian Distance Covariance in Vision-Language Models
por: Zhang, Yi, et al.
Publicado: (2026)

Variational Continual Test-Time Adaptation
por: Lyu, Fan, et al.
Publicado: (2024)

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

End-to-End Test-Time Training for Long Context
por: Tandon, Arnuv, et al.
Publicado: (2025)

Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space
por: Yi, Mingyang, et al.
Publicado: (2024)

Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment
por: Zhang, Youjia, et al.
Publicado: (2025)

TimeSAF: Towards LLM-Guided Semantic Asynchronous Fusion for Time Series Forecasting
por: Zhang, Fan, et al.
Publicado: (2026)

Test-Time Scaling with Reflective Generative Model
por: Wang, Zixiao, et al.
Publicado: (2025)

Test-Time Training on Video Streams
por: Wang, Renhao, et al.
Publicado: (2023)

Scaling over Scaling: Exploring Test-Time Scaling Plateau in Large Reasoning Models
por: Wang, Jian, et al.
Publicado: (2025)

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

Reasoning-as-Logic-Units: Scaling Test-Time Reasoning in Large Language Models Through Logic Unit Alignment
por: Li, Cheryl, et al.
Publicado: (2025)

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch
por: Gu, Hao, et al.
Publicado: (2026)

Test-Time Training Scaling Laws for Chemical Exploration in Drug Design
por: Thomas, Morgan, et al.
Publicado: (2025)