Copertina

The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lan, Xiaochong, Zheng, Yu, Cao, Shiteng, Li, Yong
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Stance Detection with Collaborative Role-Infused LLM-Based Agents
di: Lan, Xiaochong, et al.
Pubblicazione: (2023)

LocalGPT: Benchmarking and Advancing Large Language Models for Local Life Services in Meituan
di: Lan, Xiaochong, et al.
Pubblicazione: (2025)

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment
di: Lan, Xiaochong, et al.
Pubblicazione: (2025)

Depression Detection on Social Media with Large Language Models
di: Lan, Xiaochong, et al.
Pubblicazione: (2024)

An Empirical Study on Prompt Compression for Large Language Models
di: Zhang, Zheng, et al.
Pubblicazione: (2025)

The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models
di: Tan, Yuqiao, et al.
Pubblicazione: (2025)

Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models
di: Liu, Ruikang, et al.
Pubblicazione: (2025)

Do LLMs Really Think Step-by-step In Implicit Reasoning?
di: Yu, Yijiong
Pubblicazione: (2024)

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

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
di: Yong, Xixian, et al.
Pubblicazione: (2025)

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

ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
di: Yang, Junyao, et al.
Pubblicazione: (2026)

Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs
di: Su, Jinyan, et al.
Pubblicazione: (2025)

Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
di: Xu, Fengli, et al.
Pubblicazione: (2025)

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

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

Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models
di: Sreedhar, Makesh Narsimhan, et al.
Pubblicazione: (2025)

An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation
di: Shirafuji, Daiki, et al.
Pubblicazione: (2025)

SuperMerge: An Approach For Gradient-Based Model Merging
di: Yang, Haoyu, et al.
Pubblicazione: (2024)

Explore the Potential of LLMs in Misinformation Detection: An Empirical Study
di: Chen, Mengyang, et al.
Pubblicazione: (2023)

Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
di: Pipatanakul, Kunat, et al.
Pubblicazione: (2025)

Evaluating Large Language Models on Financial Report Summarization: An Empirical Study
di: Yang, Xinqi, et al.
Pubblicazione: (2024)

Reverse Thinking Makes LLMs Stronger Reasoners
di: Chen, Justin Chih-Yao, et al.
Pubblicazione: (2024)

To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks
di: Gong, Nanxu, et al.
Pubblicazione: (2026)

Read Quietly, Think Aloud: Decoupling Comprehension and Reasoning in LLMs
di: Wang, Yuanxin, et al.
Pubblicazione: (2025)

Thinking LLMs: General Instruction Following with Thought Generation
di: Wu, Tianhao, et al.
Pubblicazione: (2024)

An Empirical Study of Data Ability Boundary in LLMs' Math Reasoning
di: Chen, Zui, et al.
Pubblicazione: (2024)

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

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

LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking
di: Wu, Junhong, et al.
Pubblicazione: (2025)

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

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

Reasoning Pattern Alignment Merging for Adaptive Reasoning
di: Zhong, Zhaofeng, et al.
Pubblicazione: (2026)

RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior
di: Yang, Junyao, et al.
Pubblicazione: (2025)

Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
di: Chan, Yik Siu, et al.
Pubblicazione: (2025)

Modeling Hierarchical Thinking in Large Reasoning Models
di: Shahariar, G M, et al.
Pubblicazione: (2025)

Multi-task Code LLMs: Data Mix or Model Merge?
di: Zhu, Mingzhi, et al.
Pubblicazione: (2026)

Thinking About Thinking: Evaluating Reasoning in Post-Trained Language Models
di: Singla, Pratham, et al.
Pubblicazione: (2025)

Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging
di: Liu, Deyuan, et al.
Pubblicazione: (2024)

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