Imagen de Portada

When does Chain-of-Thought Help: A Markovian Perspective

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Zihan, Dong, Yijun, Lei, Qi
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective
por: Zhang, Yue, et al.
Publicado: (2026)

Does Weak-to-strong Generalization Happen under Spurious Correlations?
por: Liu, Chenruo, et al.
Publicado: (2025)

How does Chain of Thought decompose complex tasks?
por: Nadgir, Amrut, et al.
Publicado: (2026)

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
por: Zhu, Hanlin, et al.
Publicado: (2025)

When More is Less: Understanding Chain-of-Thought Length in LLMs
por: Wu, Yuyang, et al.
Publicado: (2025)

Scalable Chain of Thoughts via Elastic Reasoning
por: Xu, Yuhui, et al.
Publicado: (2025)

A Task-Centric Theory for Iterative Self-Improvement with Easy-to-Hard Curricula
por: Liu, Chenruo, et al.
Publicado: (2026)

When does Subagging Work?
por: Revelas, Christos, et al.
Publicado: (2024)

When Chain-of-Thought Fails, the Solution Hides in the Hidden States
por: Mehrafarin, Houman, et al.
Publicado: (2026)

The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?
por: Pengmei, Zihan, et al.
Publicado: (2025)

Honesty in Causal Forests: When It Helps and When It Hurts
por: Hou, Yanfang, et al.
Publicado: (2025)

Aligned, Orthogonal or In-conflict: When can we safely optimize Chain-of-Thought?
por: Kaufmann, Max, et al.
Publicado: (2026)

Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle
por: Wang, Zihan, et al.
Publicado: (2026)

CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning
por: Fang, Yuanheng, et al.
Publicado: (2025)

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

Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
por: Dong, Yijun, et al.
Publicado: (2024)

Fractured Chain-of-Thought Reasoning
por: Liao, Baohao, et al.
Publicado: (2025)

When does a bridge become an aeroplane?
por: Dardeno, Tina A., et al.
Publicado: (2024)

LoRA and Privacy: When Random Projections Help (and When They Don't)
por: Hu, Yaxi, et al.
Publicado: (2026)

Transformers Provably Learn to Internalize Chain-of-Thought
por: Huang, Yixiao, et al.
Publicado: (2026)

Deep Thinking by Markov Chain of Continuous Thoughts
por: Liu, Jiayu, et al.
Publicado: (2025)

On Learning Verifiers and Implications to Chain-of-Thought Reasoning
por: Balcan, Maria-Florina, et al.
Publicado: (2025)

Dynamic Chain-of-Thought: Towards Adaptive Deep Reasoning
por: Wang, Libo
Publicado: (2025)

When Does Trimming Help Conformal Prediction? A Retained-Law Diagnostic under Calibration Contamination
por: Wang, Congye
Publicado: (2026)

Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective
por: Kajitsuka, Tokio, et al.
Publicado: (2026)

When does a predictor know its own loss?
por: Gollakota, Aravind, et al.
Publicado: (2025)

A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning
por: Doron-Arad, Ilan, et al.
Publicado: (2026)

A Formal Comparison Between Chain of Thought and Latent Thought
por: Xu, Kevin, et al.
Publicado: (2025)

CTRLS: Chain-of-Thought Reasoning via Latent State-Transition
por: Wu, Junda, et al.
Publicado: (2025)

Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects
por: Cui, Yixin, et al.
Publicado: (2025)

Chain-of-Thought Predictive Control
por: Jia, Zhiwei, et al.
Publicado: (2023)

Time Series Gaussian Chain Graph Models
por: Fang, Qin, et al.
Publicado: (2026)

Elastic Representation: Mitigating Spurious Correlations for Group Robustness
por: Wen, Tao, et al.
Publicado: (2025)

Synthetic Augmentation in Imbalanced Learning: When It Helps, When It Hurts, and How Much to Add
por: Ma, Zhengchi, et al.
Publicado: (2026)

Latent Chain-of-Thought Improves Structured-Data Transformers
por: Dudley, Carson, et al.
Publicado: (2026)

Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought
por: Xie, Zixuan, et al.
Publicado: (2026)

Continuous Chain of Thought Enables Parallel Exploration and Reasoning
por: Gozeten, Halil Alperen, et al.
Publicado: (2025)

Transformers Provably Solve Parity Efficiently with Chain of Thought
por: Kim, Juno, et al.
Publicado: (2024)

Analyzing the Power of Chain of Thought through Memorization Capabilities
por: Yu, Lijia, et al.
Publicado: (2025)

Reasoning Models Sometimes Output Illegible Chains of Thought
por: Jose, Arun
Publicado: (2025)