Cover Image

The Zero-Step Thinking: An Empirical Study of Mode Selection as Harder Early Exit in Reasoning Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tan, Yuqiao, He, Shizhu, Liu, Kang, Zhao, Jun
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models
by: Tan, Yuqiao, et al.
Published: (2025)

Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
by: Tan, Yuqiao, et al.
Published: (2025)

FlashThink: An Early Exit Method For Efficient Reasoning
by: Jiang, Guochao, et al.
Published: (2025)

ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
by: Liao, Huanxuan, et al.
Published: (2026)

From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
by: Tan, Yuqiao, et al.
Published: (2026)

Dynamic Early Exit in Reasoning Models
by: Yang, Chenxu, et al.
Published: (2025)

ExpNote: Black-box Large Language Models are Better Task Solvers with Experience Notebook
by: Sun, Wangtao, et al.
Published: (2023)

Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model
by: Xia, Fei, et al.
Published: (2024)

Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns
by: Li, Xiang, et al.
Published: (2025)

Efficient Data Learning for Open Information Extraction with Pre-trained Language Models
by: Fan, Zhiyuan, et al.
Published: (2023)

ItD: Large Language Models Can Teach Themselves Induction through Deduction
by: Sun, Wangtao, et al.
Published: (2024)

DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning
by: Liao, Huanxuan, et al.
Published: (2025)

The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging
by: Lan, Xiaochong, et al.
Published: (2025)

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

Amplify Adjacent Token Differences: Enhancing Long Chain-of-Thought Reasoning with Shift-FFN
by: Xu, Yao, et al.
Published: (2025)

MixReasoning: Switching Modes to Think
by: Lu, Haiquan, et al.
Published: (2025)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
by: Yang, Rubing, et al.
Published: (2025)

On the Step Length Confounding in LLM Reasoning Data Selection
by: Wang, Bing, et al.
Published: (2026)

LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs
by: Xia, Fei, et al.
Published: (2022)

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

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

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis
by: Zhao, Yufeng, et al.
Published: (2025)

Stephanie2: Thinking, Waiting, and Making Decisions Like Humans in Step-by-Step AI Social Chat
by: Yang, Hao, et al.
Published: (2026)

ADEPT: Adaptive Dynamic Early-Exit Process for Transformers
by: Yoo, Sangmin, et al.
Published: (2026)

The Diminishing Returns of Early-Exit Decoding in Modern LLMs
by: Wei, Rui, et al.
Published: (2026)

Generate-on-Graph: Treat LLM as both Agent and KG in Incomplete Knowledge Graph Question Answering
by: Xu, Yao, et al.
Published: (2024)

Defending against Jailbreak through Early Exit Generation of Large Language Models
by: Zhao, Chongwen, et al.
Published: (2024)

Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation
by: Bao, Qiming, et al.
Published: (2022)

TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
by: Nagle, Alliot, et al.
Published: (2026)

Beyond Instruction Following: Evaluating Inferential Rule Following of Large Language Models
by: Sun, Wangtao, et al.
Published: (2024)

DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
by: Huang, Yiming, et al.
Published: (2024)

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

Overtrained Language Models Are Harder to Fine-Tune
by: Springer, Jacob Mitchell, et al.
Published: (2025)

Reasoning Models Can Be Effective Without Thinking
by: Ma, Wenjie, et al.
Published: (2025)

DAdEE: Unsupervised Domain Adaptation in Early Exit PLMs
by: Bajpai, Divya Jyoti, et al.
Published: (2024)

Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments
by: Lu, Qingyu, et al.
Published: (2025)

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

Thinking Fast, Thinking Wrong: Intuitiveness Modulates LLM Counterfactual Reasoning in Policy Evaluation
by: He, Yanjie
Published: (2026)

Disagreements in Reasoning: How a Model's Thinking Process Dictates Persuasion in Multi-Agent Systems
by: Zhao, Haodong, et al.
Published: (2025)

Thinking in Many Modes: How Composite Reasoning Elevates Large Language Model Performance with Limited Data
by: Ahmad, Zishan, et al.
Published: (2025)