Copertina

Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Wei-Lin, Peng, Liqian, Tan, Tian, Zhao, Chao, Chen, Blake JianHang, Lin, Ziqian, Go, Alec, Meng, Yu
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing
di: Zeng, Yaopei, et al.
Pubblicazione: (2026)

Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking
di: Tian, Xiaoyu, et al.
Pubblicazione: (2025)

Deep Think with Confidence
di: Fu, Yichao, et al.
Pubblicazione: (2025)

Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning
di: Zhang, Kai, et al.
Pubblicazione: (2024)

Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
di: Guo, Zhenyuan, et al.
Pubblicazione: (2026)

Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
di: Zhao, Guangxiang, et al.
Pubblicazione: (2026)

Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort
di: Wang, Xinpeng, et al.
Pubblicazione: (2025)

Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
di: Sun, Jiashuo, et al.
Pubblicazione: (2023)

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

ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization
di: Li, Sunzhu, et al.
Pubblicazione: (2025)

From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
di: Zhu, Wenxin, et al.
Pubblicazione: (2025)

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning
di: Zhu, Yekun, et al.
Pubblicazione: (2025)

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
di: Qian, Chen, et al.
Pubblicazione: (2025)

Controlling Thinking Speed in Reasoning Models
di: Lin, Zhengkai, et al.
Pubblicazione: (2025)

DeepThink: Aligning Language Models with Domain-Specific User Intents
di: Li, Yang, et al.
Pubblicazione: (2025)

Test-Time Deep Thinking to Explore Implicit Rules
di: Chen, Wentong, et al.
Pubblicazione: (2026)

Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
di: Zhou, Jiahui, et al.
Pubblicazione: (2026)

Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images
di: Yang, Wenhao, et al.
Pubblicazione: (2025)

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

ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
di: He, Qianyu, et al.
Pubblicazione: (2025)

Adaptive Deep Reasoning: Triggering Deep Thinking When Needed
di: Wang, Yunhao, et al.
Pubblicazione: (2025)

Thinking Short and Right Over Thinking Long: Serving LLM Reasoning Efficiently and Accurately
di: Wang, Yuhang, et al.
Pubblicazione: (2025)

Enhancing LLM Reasoning for Time Series Classification by Tailored Thinking and Fused Decision
di: Zhou, Jiahui, et al.
Pubblicazione: (2025)

ThinkRec: Thinking-based recommendation via LLM
di: Yu, Qihang, et al.
Pubblicazione: (2025)

Think Just Enough: Sequence-Level Entropy as a Confidence Signal for LLM Reasoning
di: Sharma, Aman, et al.
Pubblicazione: (2025)

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
di: Yin, Cheng, et al.
Pubblicazione: (2025)

Reinforcing Video Reasoning with Focused Thinking
di: Dang, Jisheng, et al.
Pubblicazione: (2025)

KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation
di: Zhang, Dalong, et al.
Pubblicazione: (2025)

Reasoning Models Don't Just Think Longer, They Move Differently
di: Gjølbye, Anders, et al.
Pubblicazione: (2026)

Not All Tokens Are What You Need In Thinking
di: Yuan, Hang, et al.
Pubblicazione: (2025)

AdaptThink: Reasoning Models Can Learn When to Think
di: Zhang, Jiajie, et al.
Pubblicazione: (2025)

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

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
di: Xiong, Zidi, et al.
Pubblicazione: (2025)

Think Dense, Not Long: Dynamic Decoupled Conditional Advantage for Efficient Reasoning
di: Peng, Keqin, et al.
Pubblicazione: (2026)

LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens
di: Zebaze, Armel, et al.
Pubblicazione: (2025)

Thinking Fast and Slow with Deep Learning and Tree Search
di: Anthony, Thomas, et al.
Pubblicazione: (2017)

Efficient Reasoning with Balanced Thinking
di: Li, Yulin, et al.
Pubblicazione: (2026)

Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
di: Yang, Wenkai, et al.
Pubblicazione: (2025)

DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
di: Guan, Xinyan, et al.
Pubblicazione: (2025)

Fast Quiet-STaR: Thinking Without Thought Tokens
di: Huang, Wei, et al.
Pubblicazione: (2025)