Copertina

Quantized Reasoning Models Think They Need to Think Longer, but They Do Not

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lotfi, Sanae, Kirichenko, Polina, Li, Steven, Liu, Zechun
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning
di: Yang, Wang, et al.
Pubblicazione: (2025)

The Relationship Between Reasoning and Performance in Large Language Models -- o3 (mini) Thinks Harder, Not Longer
di: Ballon, Marthe, et al.
Pubblicazione: (2025)

Thinking Deeper, Not Longer: Depth-Recurrent Transformers for Compositional Generalization
di: Chen, Hung-Hsuan
Pubblicazione: (2026)

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

What's in Common? Multimodal Models Hallucinate When Reasoning Across Scenes
di: Ross, Candace, et al.
Pubblicazione: (2025)

To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
di: Zhu, Zihao, et al.
Pubblicazione: (2025)

AdapThink: Adaptive Thinking Preferences for Reasoning Language Model
di: Wan, Xu, et al.
Pubblicazione: (2025)

Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner
di: He, Tao, et al.
Pubblicazione: (2025)

Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
di: Shen, Junhong, et al.
Pubblicazione: (2025)

ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models
di: Sun, Chung-En, et al.
Pubblicazione: (2025)

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

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

Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful
di: Marek, Martin, et al.
Pubblicazione: (2025)

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
di: Hong, Ilgee, et al.
Pubblicazione: (2025)

Thinking About Thinking: SAGE-nano's Inverse Reasoning for Self-Aware Language Models
di: Jha, Basab, et al.
Pubblicazione: (2025)

Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models
di: Sheng, Zhichao, et al.
Pubblicazione: (2025)

Do Latent-CoT Models Think Step-by-Step? A Mechanistic Study on Sequential Reasoning Tasks
di: Liang, Jia, et al.
Pubblicazione: (2026)

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

Trade-offs in Ensembling, Merging and Routing Among Parameter-Efficient Experts
di: Lotfi, Sanae, et al.
Pubblicazione: (2026)

MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning
di: Xi, Ningyuan, et al.
Pubblicazione: (2024)

Do Multilingual LLMs Think In English?
di: Schut, Lisa, et al.
Pubblicazione: (2025)

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

Large Reasoning Models Learn Better Alignment from Flawed Thinking
di: Peng, ShengYun, et al.
Pubblicazione: (2025)

Think, Prune, Train, Improve: Scaling Reasoning without Scaling Models
di: Costello, Caia, et al.
Pubblicazione: (2025)

Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
di: Lotfi, Sanae, et al.
Pubblicazione: (2024)

K2-Think: A Parameter-Efficient Reasoning System
di: Cheng, Zhoujun, et al.
Pubblicazione: (2025)

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

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

CoRT: Code-integrated Reasoning within Thinking
di: Li, Chengpeng, et al.
Pubblicazione: (2025)

Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
di: Yang, Dayu, et al.
Pubblicazione: (2025)

Effectively Controlling Reasoning Models through Thinking Intervention
di: Wu, Tong, et al.
Pubblicazione: (2025)

Reasoning Models Don't Always Say What They Think
di: Chen, Yanda, et al.
Pubblicazione: (2025)

Don't Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
di: An, Sohyun, et al.
Pubblicazione: (2025)

OverThink: Slowdown Attacks on Reasoning LLMs
di: Kumar, Abhinav, et al.
Pubblicazione: (2025)

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

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

Thinking as Emergence: How AI Begins to Think in Response, Resistance, and Relationship
di: Molchanova, Olena, et al.
Pubblicazione: (2025)

PARQ: Piecewise-Affine Regularized Quantization
di: Jin, Lisa, et al.
Pubblicazione: (2025)

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