Buchumschlag

Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoning

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Sui, Yi, Li, Chaozhuo, Song, Dawei
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge
von: Sui, Yi, et al.
Veröffentlicht: (2025)

LIMO: Less is More for Reasoning
von: Ye, Yixin, et al.
Veröffentlicht: (2025)

Less is More Tokens: Efficient Math Reasoning via Difficulty-Aware Chain-of-Thought Distillation
von: Waheed, Abdul, et al.
Veröffentlicht: (2025)

Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
von: Shrivastava, Vaishnavi, et al.
Veröffentlicht: (2025)

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
von: Zhao, Weixiang, et al.
Veröffentlicht: (2025)

ThinkLess: A Training-Free Inference-Efficient Method for Reducing Reasoning Redundancy
von: Li, Gengyang, et al.
Veröffentlicht: (2025)

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
von: Liu, Chengzhi, et al.
Veröffentlicht: (2025)

Acting Less is Reasoning More! Teaching Model to Act Efficiently
von: Wang, Hongru, et al.
Veröffentlicht: (2025)

Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
von: Tan, Wenhui, et al.
Veröffentlicht: (2025)

Less is More: Compact Clue Selection for Efficient Retrieval-Augmented Generation Reasoning
von: Zhang, Qianchi, et al.
Veröffentlicht: (2025)

LimRank: Less is More for Reasoning-Intensive Information Reranking
von: Song, Tingyu, et al.
Veröffentlicht: (2025)

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
von: Song, Jiwon, et al.
Veröffentlicht: (2025)

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
von: Xu, Xin, et al.
Veröffentlicht: (2025)

PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning
von: Feng, Ruixiang, et al.
Veröffentlicht: (2026)

Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance
von: Yu, Jiachen, et al.
Veröffentlicht: (2026)

DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models
von: Jiang, Yuxuan, et al.
Veröffentlicht: (2025)

Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinking
von: Cheng, Xiaoxue, et al.
Veröffentlicht: (2025)

Aware First, Think Less: Dynamic Boundary Self-Awareness Drives Extreme Reasoning Efficiency in Large Language Models
von: Chen, Qiguang, et al.
Veröffentlicht: (2025)

Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs
von: Xiao, Yilin, et al.
Veröffentlicht: (2025)

More or Less Wrong: A Benchmark for Directional Bias in LLM Comparative Reasoning
von: Shafiei, Mohammadamin, et al.
Veröffentlicht: (2025)

Efficient Reasoning with Balanced Thinking
von: Li, Yulin, et al.
Veröffentlicht: (2026)

Adaptive Loops and Memory in Transformers: Think Harder or Know More?
von: Frey, Markus, et al.
Veröffentlicht: (2026)

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention
von: Yang, Zhen, et al.
Veröffentlicht: (2025)

Breadcrumbs Reasoning: Memory-Efficient Reasoning with Compression Beacons
von: Monea, Giovanni, et al.
Veröffentlicht: (2025)

Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model
von: Ding, Bowen, et al.
Veröffentlicht: (2025)

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains
von: Xie, Hui, et al.
Veröffentlicht: (2026)

Thinking Out Loud: Do Reasoning Models Know When They're Right?
von: Zeng, Qingcheng, et al.
Veröffentlicht: (2025)

TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers' Guidance
von: Xu, Jingxian, et al.
Veröffentlicht: (2025)

Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
von: Abdaljalil, Samir, et al.
Veröffentlicht: (2026)

Knowledge Updating? No More Model Editing! Just Selective Contextual Reasoning
von: He, Guoxiu, et al.
Veröffentlicht: (2025)

Think Beyond Size: Adaptive Prompting for More Effective Reasoning
von: R, Kamesh
Veröffentlicht: (2024)

KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning
von: Dang, Xilin, et al.
Veröffentlicht: (2025)

Less Is More: Fast and Accurate Reasoning with Cross-Head Unified Sparse Attention
von: Yang, Lijie, et al.
Veröffentlicht: (2025)

Reasoning on Efficient Knowledge Paths:Knowledge Graph Guides Large Language Model for Domain Question Answering
von: Wang, Yuqi, et al.
Veröffentlicht: (2024)

Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMs
von: Chen, Kang, et al.
Veröffentlicht: (2025)

Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models
von: Li, Junyi, et al.
Veröffentlicht: (2025)

Latent Reasoning with Supervised Thinking States
von: Amos, Ido, et al.
Veröffentlicht: (2026)

When More Is Less: A Systematic Analysis of Spatial and Commonsense Information for Visual Spatial Reasoning
von: Akasaka, Muku, et al.
Veröffentlicht: (2026)

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
von: Chen, Qianben, et al.
Veröffentlicht: (2026)

Efficient Reasoning with Hidden Thinking
von: Shen, Xuan, et al.
Veröffentlicht: (2025)