Cover Image

When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Jiaqi, Guo, Xuehang, Yu, Pengfei, Zhang, Xiang, Ouyang, Wanli, Sun, Siqi, Wang, Qingyun, You, Chenyu
Format:	Preprint
Published:	2026
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey
by: Wei, Jiaqi, et al.
Published: (2025)

Beyond Words: Multimodal LLM Knows When to Speak
by: Liao, Zikai, et al.
Published: (2025)

Thinkless: LLM Learns When to Think
by: Fang, Gongfan, et al.
Published: (2025)

Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
by: Wei, Jiaqi, et al.
Published: (2025)

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

Anagent For Enhancing Scientific Table & Figure Analysis
by: Guo, Xuehang, et al.
Published: (2026)

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

TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
by: Li, Yinxi, et al.
Published: (2025)

When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs
by: Li, Xiaomin, et al.
Published: (2025)

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
by: Zhu, Rongzhi, et al.
Published: (2025)

ThinkSwitcher: When to Think Hard, When to Think Fast
by: Liang, Guosheng, et al.
Published: (2025)

When to Speak, When to Abstain: Contrastive Decoding with Abstention
by: Kim, Hyuhng Joon, et al.
Published: (2024)

Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits
by: Zhang, Xiang, et al.
Published: (2025)

Cognitive Decision Routing in Large Language Models: When to Think Fast, When to Think Slow
by: Du, Y., et al.
Published: (2025)

When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning
by: Xiang, Yang, et al.
Published: (2026)

When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
by: Wang, Kai, et al.
Published: (2025)

Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
by: Zhang, Xiang, et al.
Published: (2025)

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning
by: Zhang, Xiaoyun, et al.
Published: (2025)

Think Only When You Need with Large Hybrid-Reasoning Models
by: Jiang, Lingjie, et al.
Published: (2025)

DiscussLLM: Teaching Large Language Models When to Speak
by: Patel, Deep Anil, et al.
Published: (2025)

When to Think and When to Look: Uncertainty-Guided Lookback
by: Bi, Jing, et al.
Published: (2025)

LLM Agents Already Know When to Call Tools -- Even Without Reasoning
by: Sun, Chung-En, et al.
Published: (2026)

Learning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning
by: Xiong, Juming, et al.
Published: (2026)

When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment
by: Yan, Hanqi, et al.
Published: (2025)

When Abundance Conceals Weakness: Knowledge Conflict in Multilingual Models
by: Zhao, Jiaqi, et al.
Published: (2026)

When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning
by: Sheng, Leheng, et al.
Published: (2026)

SciDER: Scientific Data-centric End-to-end Researcher
by: Lin, Ke, et al.
Published: (2026)

Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs
by: Zhang, Xiang, et al.
Published: (2025)

VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format
by: Wang, Yueqian, et al.
Published: (2024)

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

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

When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning
by: Singhi, Nishad, et al.
Published: (2025)

Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking
by: Guo, Huizhong, et al.
Published: (2026)

Perception-Aware Policy Optimization for Multimodal Reasoning
by: Wang, Zhenhailong, et al.
Published: (2025)

Large Language Models Know What To Say But Not When To Speak
by: Umair, Muhammad, et al.
Published: (2024)

When Reasoning Meets Its Laws
by: Zhang, Junyu, et al.
Published: (2025)

When to Reason: Semantic Router for vLLM
by: Wang, Chen, et al.
Published: (2025)

Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning
by: Wu, Shu, et al.
Published: (2025)

Think When You Need: Self-Adaptive Chain-of-Thought Learning
by: Yang, Junjie, et al.
Published: (2025)

When Misinformation Speaks and Converses: Rethinking Fact-Checking in Audio Platforms
by: Chun, Chaewan, et al.
Published: (2026)