Copertina

Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Zeju, Zhong, Jianyuan, Zheng, Ziyang, Wen, Xiangyu, Xu, Zhijian, Cheng, Yingying, Zhang, Fan, Xu, Qiang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Dyve: Thinking Fast and Slow for Dynamic Process Verification
di: Zhong, Jianyuan, et al.
Pubblicazione: (2025)

Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier
di: Zhong, Jianyuan, et al.
Pubblicazione: (2025)

Reasoning Scaffolding: Distilling the Flow of Thought from LLMs
di: Wen, Xiangyu, et al.
Pubblicazione: (2025)

From Craft to Constitution: A Governance-First Paradigm for Principled Agent Engineering
di: Xu, Qiang, et al.
Pubblicazione: (2025)

Context Distillation as Latent Memory Management
di: Zheng, Ziyang, et al.
Pubblicazione: (2026)

Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow
di: Moore, Kyle, et al.
Pubblicazione: (2024)

DeepGate3: Towards Scalable Circuit Representation Learning
di: Shi, Zhengyuan, et al.
Pubblicazione: (2024)

Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents
di: Yang, Ruihan, et al.
Pubblicazione: (2026)

Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
di: Liu, Ryan, et al.
Pubblicazione: (2024)

DSPO: An End-to-End Framework for Direct Sorted Portfolio Construction
di: Zhong, Jianyuan, et al.
Pubblicazione: (2024)

AtomThink: Multimodal Slow Thinking with Atomic Step Reasoning
di: Xiang, Kun, et al.
Pubblicazione: (2024)

Slow Tuning and Low-Entropy Masking for Safe Chain-of-Thought Distillation
di: Ma, Ziyang, et al.
Pubblicazione: (2025)

ICPC: In-context Prompt Compression with Faster Inference
di: Yu, Ziyang, et al.
Pubblicazione: (2025)

PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation
di: Fan, Tao, et al.
Pubblicazione: (2025)

When to Think Fast and Slow? AMOR: Adaptive Entropy Gate for Hybrid Models
di: Zheng, Haoran, et al.
Pubblicazione: (2026)

COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion
di: Deng, Zihan, et al.
Pubblicazione: (2026)

RuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step
di: Luo, Xiaocheng, et al.
Pubblicazione: (2026)

Latent Context Compilation: Distilling Long Context into Compact Portable Memory
di: Li, Zeju, et al.
Pubblicazione: (2026)

LightThinker: Thinking Step-by-Step Compression
di: Zhang, Jintian, et al.
Pubblicazione: (2025)

DSADF: Thinking Fast and Slow for Decision Making
di: Dou, Zhihao, et al.
Pubblicazione: (2025)

M-RAG: Making RAG Faster, Stronger, and More Efficient
di: Xu, Sun, et al.
Pubblicazione: (2026)

MyGO Multiplex CoT: A Method for Self-Reflection in Large Language Models via Double Chain of Thought Thinking
di: Ji, Shihao, et al.
Pubblicazione: (2025)

Reason from Future: Reverse Thought Chain Enhances LLM Reasoning
di: Xu, Yinlong, et al.
Pubblicazione: (2025)

Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities
di: Menon, Sachit, et al.
Pubblicazione: (2024)

Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning
di: Chen, Yiqun, et al.
Pubblicazione: (2026)

Enhancing Decision-Making for LLM Agents via Step-Level Q-Value Models
di: Zhai, Yuanzhao, et al.
Pubblicazione: (2024)

Upfront Chain-of-Thought: A Cooperative Framework for Chain-of-Thought Compression
di: Li, Chengzhengxu, et al.
Pubblicazione: (2025)

TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision
di: Zhou, Ruiwen, et al.
Pubblicazione: (2024)

Think Step by Step: Chain-of-Gesture Prompting for Error Detection in Robotic Surgical Videos
di: Shao, Zhimin, et al.
Pubblicazione: (2024)

MTMT: Consolidating Multiple Thinking Modes to Form a Thought Tree for Strengthening LLM
di: Li, Changcheng, et al.
Pubblicazione: (2024)

SleepCoT: A Lightweight Personalized Sleep Health Model via Chain-of-Thought Distillation
di: Zheng, Huimin, et al.
Pubblicazione: (2024)

Activation Steering for Chain-of-Thought Compression
di: Azizi, Seyedarmin, et al.
Pubblicazione: (2025)

ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning
di: Hu, Minda, et al.
Pubblicazione: (2026)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
di: Chen, Xi, et al.
Pubblicazione: (2025)

Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs
di: Cao, Jie, et al.
Pubblicazione: (2026)

Markov Chain of Thought for Efficient Mathematical Reasoning
di: Yang, Wen, et al.
Pubblicazione: (2024)

Chain Of Thought Compression: A Theoretical Analysis
di: Li, Juncai, et al.
Pubblicazione: (2026)

Let's Think with Images Efficiently! An Interleaved-Modal Chain-of-Thought Reasoning Framework with Dynamic and Precise Visual Thoughts
di: Liu, Xu, et al.
Pubblicazione: (2026)

Lemur: Log Parsing with Entropy Sampling and Chain-of-Thought Merging
di: Zhang, Wei, et al.
Pubblicazione: (2024)

Slow Thinking for Sequential Recommendation
di: Zhang, Junjie, et al.
Pubblicazione: (2025)