Copertina

How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhai, Zhiyuan, You, Xinkai, Yan, Wenjing, Wang, Xin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

How Much Data Is Enough? Uniform Convergence Bounds for Generative & Vision-Language Models under Low-Dimensional Structure
di: Thompson, Paul M.
Pubblicazione: (2025)

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning
di: Xiang, Violet, et al.
Pubblicazione: (2025)

Think Clearly: Improving Reasoning via Redundant Token Pruning
di: Choi, Daewon, et al.
Pubblicazione: (2025)

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
di: He, Haoran, et al.
Pubblicazione: (2025)

How Much Data is Enough? The Zeta Law of Discoverability in Biomedical Data, featuring the enigmatic Riemann zeta function
di: Thompson, Paul M.
Pubblicazione: (2026)

DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models
di: Shen, Yi, et al.
Pubblicazione: (2025)

Quantifying and Understanding Uncertainty in Large Reasoning Models
di: Li, Yangyi, et al.
Pubblicazione: (2026)

How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers
di: Wang, Xiao
Pubblicazione: (2026)

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning
di: Cai, Hongyi James, et al.
Pubblicazione: (2025)

Understanding Reasoning in Thinking Language Models via Steering Vectors
di: Venhoff, Constantin, et al.
Pubblicazione: (2025)

Infinite Width Models That Work: Why Feature Learning Doesn't Matter as Much as You Think
di: Sernau, Luke
Pubblicazione: (2024)

Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
di: Yang, Zhicheng, et al.
Pubblicazione: (2026)

Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning
di: Gao, Hang, et al.
Pubblicazione: (2025)

Base Models Know How to Reason, Thinking Models Learn When
di: Venhoff, Constantin, et al.
Pubblicazione: (2025)

Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory
di: Dong, Songwei, et al.
Pubblicazione: (2026)

Locality-Aware Redundancy Pruning for LLM Depth Compression
di: Yun, Vincent-Daniel, et al.
Pubblicazione: (2026)

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

Structural Reasoning Improves Molecular Understanding of LLM
di: Jang, Yunhui, et al.
Pubblicazione: (2024)

Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
di: Balef, Amir Rezaei, et al.
Pubblicazione: (2026)

When, How Long and How Much? Interpretable Neural Networks for Time Series Regression by Learning to Mask and Aggregate
di: Forest, Florent, et al.
Pubblicazione: (2025)

How Much is Too Much? Exploring LoRA Rank Trade-offs for Retaining Knowledge and Domain Robustness
di: Rathore, Darshita, et al.
Pubblicazione: (2025)

Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy
di: Gao, Shujian, et al.
Pubblicazione: (2026)

Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
di: Lawsen, A.
Pubblicazione: (2025)

ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
di: Xu, Xin, et al.
Pubblicazione: (2026)

Think Before You Lie: How Reasoning Leads to Honesty
di: Yuan, Ann, et al.
Pubblicazione: (2026)

Do Large Language Models Know How Much They Know?
di: Prato, Gabriele, et al.
Pubblicazione: (2025)

How Much Can We Forget about Data Contamination?
di: Bordt, Sebastian, et al.
Pubblicazione: (2024)

How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts
di: Park, Sumin, et al.
Pubblicazione: (2025)

AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models
di: Wang, Xiangqi, et al.
Pubblicazione: (2025)

Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems
di: Ross, Brendan Leigh, et al.
Pubblicazione: (2025)

Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
di: Jing, Zihao, et al.
Pubblicazione: (2026)

Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning
di: Wei, Lei, et al.
Pubblicazione: (2026)

Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor
di: Liu, Siyuan, et al.
Pubblicazione: (2025)

Efficient Reasoning with Hidden Thinking
di: Shen, Xuan, et al.
Pubblicazione: (2025)

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
di: Zhang, Mohan, et al.
Pubblicazione: (2025)

Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options
di: Nair, Lakshmi, et al.
Pubblicazione: (2025)

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

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

How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots
di: Yu, Hang, et al.
Pubblicazione: (2024)