Copertina

Zero Token-Driven Deep Thinking in LLMs: Unlocking the Full Potential of Existing Parameters via Cyclic Refinement

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Guanghao, Jiang, Wenhao, Shen, Li, Tang, Ming, Yuan, Chun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Unlocking Recursive Thinking of LLMs: Alignment via Refinement
di: Zhang, Haoke, et al.
Pubblicazione: (2025)

DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding
di: Li, Guanghao, et al.
Pubblicazione: (2025)

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
di: Zhang, Zhen, et al.
Pubblicazione: (2025)

Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration
di: Deng, Wenhao, et al.
Pubblicazione: (2025)

On the Emergence of Thinking in LLMs I: Searching for the Right Intuition
di: Ye, Guanghao, et al.
Pubblicazione: (2025)

Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority
di: Shen, Zhanming, et al.
Pubblicazione: (2026)

ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
di: Han, Feijiang, et al.
Pubblicazione: (2025)

Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
di: Tang, Yao, et al.
Pubblicazione: (2026)

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings
di: Wang, Duo, et al.
Pubblicazione: (2024)

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
di: Li, Ziniu, et al.
Pubblicazione: (2025)

Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction
di: Xu, Jun, et al.
Pubblicazione: (2025)

Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization
di: Li, Zhecheng, et al.
Pubblicazione: (2024)

Thinking in Latents: Adaptive Anchor Refinement for Implicit Reasoning in LLMs
di: Sheshanarayana, Disha, et al.
Pubblicazione: (2026)

Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models
di: Liu, Zeyu, et al.
Pubblicazione: (2025)

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

Let LLMs Speak Embedding Languages: Generative Text Embeddings via Iterative Contrastive Refinement
di: Tsai, Yu-Che, et al.
Pubblicazione: (2025)

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
di: Huang, Haoyu, et al.
Pubblicazione: (2026)

Metaphors We Compute By: A Computational Audit of Cultural Translation vs. Thinking in LLMs
di: Chang, Yuan, et al.
Pubblicazione: (2026)

Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs
di: Yang, Hongming, et al.
Pubblicazione: (2025)

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
di: Shi, Yaorui, et al.
Pubblicazione: (2025)

SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
di: Li, Guanghao, et al.
Pubblicazione: (2025)

What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
di: Li, Ming, et al.
Pubblicazione: (2024)

Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMs
di: Li, Zhuo, et al.
Pubblicazione: (2024)

SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
di: Sun, Huashan, et al.
Pubblicazione: (2025)

Thinking Tokens for Language Modeling
di: Herel, David, et al.
Pubblicazione: (2024)

From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning
di: Li, Yafu, et al.
Pubblicazione: (2025)

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey
di: Li, Jindong, et al.
Pubblicazione: (2025)

Unlocking the Potential: Benchmarking Large Language Models in Water Engineering and Research
di: Xu, Boyan, et al.
Pubblicazione: (2024)

Unlocking the Power of Large Language Models for Entity Alignment
di: Jiang, Xuhui, et al.
Pubblicazione: (2024)

ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking
di: Li, Baixuan, et al.
Pubblicazione: (2025)

SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes
di: Xie, Wenxuan, et al.
Pubblicazione: (2025)

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

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing
di: Chai, Ziwei, et al.
Pubblicazione: (2024)

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

Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design
di: Zhu, Bin, et al.
Pubblicazione: (2026)

Semantic Refinement with LLMs for Graph Representations
di: Thapaliya, Safal, et al.
Pubblicazione: (2025)

Unlocking Full Efficiency of Token Filtering in Large Language Model Training
di: Chai, Di, et al.
Pubblicazione: (2025)

TokenSkip: Controllable Chain-of-Thought Compression in LLMs
di: Xia, Heming, et al.
Pubblicazione: (2025)

PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching
di: Chen, Ruishuo, et al.
Pubblicazione: (2026)

SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs
di: Shi, Dachuan, et al.
Pubblicazione: (2025)