Cover Image

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Zhensheng, Li, Xinze, Ji, Yifan, Peng, Chunyi, Liu, Zhenghao, Shi, Qi, Yan, Yukun, Wang, Shuo, Peng, Furong, Yu, Ge
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization
by: Wang, Haolan, et al.
Published: (2025)

ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment
by: Yang, Hao, et al.
Published: (2026)

Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains
by: Xiong, Yuqi, et al.
Published: (2026)

Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
by: Duan, Shaohua, et al.
Published: (2025)

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
by: Wang, Xiyao, et al.
Published: (2024)

Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression
by: Li, Xinze, et al.
Published: (2024)

Mixture-of-Retrieval Experts for Reasoning-Guided Multimodal Knowledge Exploitation
by: Peng, Chunyi, et al.
Published: (2025)

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
by: Huang, Weiyang, et al.
Published: (2026)

Long-Chain Reasoning Distillation via Adaptive Prefix Alignment
by: Liu, Zhenghao, et al.
Published: (2026)

Stepwise Reasoning Error Disruption Attack of LLMs
by: Peng, Jingyu, et al.
Published: (2024)

VisRAG 2.0: Evidence-Guided Multi-Image Reasoning in Visual Retrieval-Augmented Generation
by: Sun, Yubo, et al.
Published: (2025)

MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization
by: Xin, Haidong, et al.
Published: (2026)

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis
by: Yang, Weiqing, et al.
Published: (2024)

Building A Coding Assistant via the Retrieval-Augmented Language Model
by: Li, Xinze, et al.
Published: (2024)

Legal$Δ$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
by: Dai, Xin, et al.
Published: (2025)

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
by: Chen, Hao, et al.
Published: (2025)

RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards
by: Li, Xinze, et al.
Published: (2024)

Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
by: Li, Xintong, et al.
Published: (2026)

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards
by: Su, Jinyan, et al.
Published: (2025)

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts
by: Wu, Mingyan, et al.
Published: (2025)

LISRec: Modeling User Preferences with Learned Item Shortcuts for Sequential Recommendation
by: Xin, Haidong, et al.
Published: (2025)

Structured Knowledge Representation through Contextual Pages for Retrieval-Augmented Generation
by: Li, Xinze, et al.
Published: (2026)

Predictive Preference Learning from Human Interventions
by: Cai, Haoyuan, et al.
Published: (2025)

Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection
by: Wu, Zhuoyang, et al.
Published: (2025)

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
by: Lai, Xin, et al.
Published: (2024)

Learning-Augmented Streaming Algorithms for Approximating MAX-CUT
by: Dong, Yinhao, et al.
Published: (2024)

Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
by: Wu, Zhenyu, et al.
Published: (2024)

\texttt{ReMind}: Understanding Deductive Code Reasoning in LLMs
by: Gao, Jun, et al.
Published: (2025)

Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction
by: Gao, Xingjie, et al.
Published: (2026)

Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs
by: Ma, Maotian, et al.
Published: (2026)

Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement
by: Liu, Chengyuan, et al.
Published: (2025)

Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models
by: Liu, Shuliang, et al.
Published: (2025)

Temporally Unified Adversarial Perturbations for Time Series Forecasting
by: Su, Ruixian, et al.
Published: (2026)

UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning
by: Wang, Yifan, et al.
Published: (2026)

Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports
by: Wei, Yishu, et al.
Published: (2026)

LeanPO: Lean Preference Optimization for Likelihood Alignment in Video-LLMs
by: Wang, Xiaodong, et al.
Published: (2025)

Length Desensitization in Direct Preference Optimization
by: Liu, Wei, et al.
Published: (2024)

Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization
by: Kawakami, Wataru, et al.
Published: (2025)

SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generation
by: Zhang, Xin, et al.
Published: (2026)

The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
by: Català, Mar Gonzàlez I, et al.
Published: (2026)