Imagen de Portada

Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Zewei, Gao, Lirong, Zhu, Yuke, Zheng, Bo, Zhao, Junbo, Guo, Sheng, Wang, Haobo
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts
por: Wang, Xinyi, et al.
Publicado: (2025)

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty
por: Ling, Zehui, et al.
Publicado: (2025)

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization
por: Zhang, Qi, et al.
Publicado: (2025)

Adaptive Stopping for Multi-Turn LLM Reasoning
por: Zhou, Xiaofan, et al.
Publicado: (2026)

BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
por: Yang, Junxiao, et al.
Publicado: (2025)

Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models
por: Yu, Longxuan, et al.
Publicado: (2026)

Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning
por: Zhang, Zhihan, et al.
Publicado: (2024)

Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation
por: Xia, Mingxuan, et al.
Publicado: (2025)

Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning
por: Liang, Qiao, et al.
Publicado: (2026)

DORY: Deliberative Prompt Recovery for LLM
por: Gao, Lirong, et al.
Publicado: (2024)

Shorten After You're Right: Lazy Length Penalties for Reasoning RL
por: Yuan, Danlong, et al.
Publicado: (2025)

REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization
por: Tang, Yiwen, et al.
Publicado: (2025)

QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism
por: Wang, Bo, et al.
Publicado: (2024)

Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs
por: Yang, Shu, et al.
Publicado: (2025)

TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping
por: Belkhiter, Yannis, et al.
Publicado: (2026)

Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning
por: Quamar, Mohammad Atif, et al.
Publicado: (2025)

Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoning
por: Sun, Renliang, et al.
Publicado: (2025)

MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning
por: Zhao, Yusheng, et al.
Publicado: (2025)

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves
por: Puerto, Haritz, et al.
Publicado: (2026)

D.Va: Validate Your Demonstration First Before You Use It
por: Zhang, Qi, et al.
Publicado: (2025)

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models
por: Liu, Kaiyuan, et al.
Publicado: (2025)

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
por: Gu, Yu, et al.
Publicado: (2026)

ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
por: Li, Kunquan, et al.
Publicado: (2026)

Rethinking Reflection in Pre-Training
por: AI, Essential, et al.
Publicado: (2025)

RECOST: External Knowledge Guided Data-efficient Instruction Tuning
por: Zhang, Qi, et al.
Publicado: (2024)

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models
por: Wu, Wei, et al.
Publicado: (2026)

Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning
por: Srinivasan, Tejas, et al.
Publicado: (2024)

Train It and Forget It: Merge Lists are Unnecessary for BPE Inference in Language Models
por: Sawada, Tomohiro, et al.
Publicado: (2025)

Unlocking Fine-Grained Translation Quality Estimation in LRMs through Synergistically Evolving Implicit and Explicit Reasoning
por: Dang, Renfei, et al.
Publicado: (2026)

REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning
por: Deng, Hexuan, et al.
Publicado: (2025)

PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection
por: Cheng, Siyuan, et al.
Publicado: (2026)

Reasoning: From Reflection to Solution
por: Li, Zixi
Publicado: (2025)

Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning
por: Yu, Yahan, et al.
Publicado: (2026)

Instruct-of-Reflection: Enhancing Large Language Models Iterative Reflection Capabilities via Dynamic-Meta Instruction
por: Liu, Liping, et al.
Publicado: (2025)

Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
por: Liu, Wei, et al.
Publicado: (2025)

MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction
por: Huang, Yue, et al.
Publicado: (2025)

FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving
por: Chen, Guizhen, et al.
Publicado: (2025)

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning
por: Zhang, Shenao, et al.
Publicado: (2025)

Efficient Reasoning for Large Reasoning Language Models via Certainty-Guided Reflection Suppression
por: Huang, Jiameng, et al.
Publicado: (2025)

TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement
por: He, Haoyang, et al.
Publicado: (2026)