Cover Image

One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Yixiao, Cheng, Dongzhou, wu, zhiliang, Yang, Yi, Cheng, Yu, Fan, Hehe
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dropping Experts, Recombining Neurons: Retraining-Free Pruning for Sparse Mixture-of-Experts LLMs
by: Zhou, Yixiao, et al.
Published: (2025)

Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL
by: Zhou, Yixiao, et al.
Published: (2026)

One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning
by: Li, Yiyuan, et al.
Published: (2026)

ProRefine: Inference-Time Prompt Refinement with Textual Feedback
by: Pandita, Deepak, et al.
Published: (2025)

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
by: Huang, Haoyu, et al.
Published: (2026)

TimeRefine: Temporal Grounding with Time Refining Video LLM
by: Wang, Xizi, et al.
Published: (2024)

Trigger$^3$: Refining Query Correction via Adaptive Model Selector
by: Zhang, Kepu, et al.
Published: (2024)

Unlocking Recursive Thinking of LLMs: Alignment via Refinement
by: Zhang, Haoke, et al.
Published: (2025)

Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement
by: Zhang, Dongxu, et al.
Published: (2026)

Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization
by: Uzan, Omri, et al.
Published: (2025)

One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry
by: Zhao, Weisong, et al.
Published: (2026)

Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models
by: Cong, Youan, et al.
Published: (2024)

One RL to See Them All: Visual Triple Unified Reinforcement Learning
by: Ma, Yan, et al.
Published: (2025)

Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning
by: Wang, Guangzhi, et al.
Published: (2025)

Enhancing Large Language Models through Structured Reasoning
by: Dong, Yubo, et al.
Published: (2025)

One Whisper to Grade Them All
by: Phan, Nhan, et al.
Published: (2025)

Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs
by: Wang, Qibin, et al.
Published: (2025)

Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinement
by: Wang, Xiaohua, et al.
Published: (2024)

Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs
by: Yang, Wanli, et al.
Published: (2026)

Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming
by: Liu, Jiaxu, et al.
Published: (2024)

One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers
by: Abagyan, Diana, et al.
Published: (2025)

OmniCaptioner: One Captioner to Rule Them All
by: Lu, Yiting, et al.
Published: (2025)

Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs
by: Puerto, Haritz, et al.
Published: (2024)

RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation
by: Chan, Chi-Min, et al.
Published: (2024)

OThink-SRR1: Search, Refine and Reasoning with Reinforced Learning for Large Language Models
by: Liang, Haijian, et al.
Published: (2026)

One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation
by: Siledar, Tejpalsingh, et al.
Published: (2024)

Training Language Model to Critique for Better Refinement
by: Yu, Tianshu, et al.
Published: (2025)

Critique-Guided Distillation for Robust Reasoning via Refinement
by: Kapusuzoglu, Berkcan, et al.
Published: (2025)

RefineBench: Evaluating Refinement Capability of Language Models via Checklists
by: Lee, Young-Jun, et al.
Published: (2025)

Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
by: Zeng, Yongcheng, et al.
Published: (2025)

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
by: Xi, Zhiheng, et al.
Published: (2023)

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
by: Shi, Yaorui, et al.
Published: (2025)

Review of Inference-Time Scaling Strategies: Reasoning, Search and RAG
by: Wang, Zhichao, et al.
Published: (2025)

RAIR: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction
by: Liang, Junhong, et al.
Published: (2025)

CoRefine: Confidence-Guided Self-Refinement for Adaptive Test-Time Compute
by: Jin, Chen, et al.
Published: (2026)

Tagging the Thought: Unlocking Personalization Reasoning via Reinforcement Learning
by: Jin, Song, et al.
Published: (2025)

GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning
by: Chen, Yi, et al.
Published: (2025)

One LLM to Train Them All: Multi-Task Learning Framework for Fact-Checking
by: Larsson, Malin Astrid, et al.
Published: (2026)

KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
by: Li, Yongjian, et al.
Published: (2025)

Query-OPT: Optimizing Inference of Large Language Models via Multi-Query Instructions in Meeting Summarization
by: Laskar, Md Tahmid Rahman, et al.
Published: (2024)