Cover Image

Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mirtaheri, Parsa, Edelman, Ezra, Jelassi, Samy, Malach, Eran, Boix-Adsera, Enric
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Repeat After Me: Transformers are Better than State Space Models at Copying
by: Jelassi, Samy, et al.
Published: (2024)

The Role of Sparsity for Length Generalization in Transformers
by: Golowich, Noah, et al.
Published: (2025)

Secret mixtures of experts inside your LLM
by: Boix-Adsera, Enric
Published: (2025)

On the inductive bias of infinite-depth ResNets and the bottleneck rank
by: Boix-Adsera, Enric
Published: (2025)

Towards a theory of model distillation
by: Boix-Adsera, Enric
Published: (2024)

When can transformers reason with abstract symbols?
by: Boix-Adsera, Enric, et al.
Published: (2023)

Toward universal steering and monitoring of AI models
by: Beaglehole, Daniel, et al.
Published: (2025)

Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing
by: Mirtaheri, Parsa, et al.
Published: (2026)

The power of fine-grained experts: Granularity boosts expressivity in Mixture of Experts
by: Boix-Adsera, Enric, et al.
Published: (2025)

LoRA Soups: Merging LoRAs for Practical Skill Composition Tasks
by: Prabhakar, Akshara, et al.
Published: (2024)

The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
by: Edelman, Benjamin L., et al.
Published: (2024)

Auto-Regressive Next-Token Predictors are Universal Learners
by: Malach, Eran
Published: (2023)

To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning
by: Qin, Tian, et al.
Published: (2025)

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

Universal Length Generalization with Turing Programs
by: Hou, Kaiying, et al.
Published: (2024)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
by: Chen, Xi, et al.
Published: (2025)

The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations
by: Boix-Adsera, Enric, et al.
Published: (2025)

Thinking Traps in Long Chain-of-Thought: A Measurable Study and Trap-Aware Adaptive Restart
by: Chen, Kang, et al.
Published: (2026)

Chain of Thought Still Thinks Fast: APriCoT Helps with Thinking Slow
by: Moore, Kyle, et al.
Published: (2024)

Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?
by: Young, Richard J.
Published: (2026)

Can Separators Improve Chain-of-Thought Prompting?
by: Park, Yoonjeong, et al.
Published: (2024)

Chain-of-Defensive-Thought: Structured Reasoning Elicits Robustness in Large Language Models against Reference Corruption
by: Wang, Wenxiao, et al.
Published: (2025)

Loss-to-Loss Prediction: Scaling Laws for All Datasets
by: Brandfonbrener, David, et al.
Published: (2024)

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
by: Zaman, Kerem, et al.
Published: (2025)

The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning
by: Chen, Qiguang, et al.
Published: (2026)

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
by: Zhao, Rosie, et al.
Published: (2025)

SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
by: Jiang, Fengqing, et al.
Published: (2025)

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

Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought
by: Xiang, Violet, et al.
Published: (2025)

Long Chain-of-Thought Reasoning Across Languages
by: Barua, Josh, et al.
Published: (2025)

The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
by: Abbe, Emmanuel, et al.
Published: (2022)

Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation
by: Khalifa, Muhammad, et al.
Published: (2026)

Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation
by: Zhong, Shanshan, et al.
Published: (2023)

DRT: Deep Reasoning Translation via Long Chain-of-Thought
by: Wang, Jiaan, et al.
Published: (2024)

Towards Automatic Evaluation of Task-Oriented Dialogue Flows
by: Mirtaheri, Mehrnoosh, et al.
Published: (2024)

Think Consistently, Reason Efficiently: Energy-Based Calibration for Implicit Chain-of-Thought
by: Chen, Zhikang, et al.
Published: (2025)

Prompts have evil twins
by: Melamed, Rimon, et al.
Published: (2023)

Upfront Chain-of-Thought: A Cooperative Framework for Chain-of-Thought Compression
by: Li, Chengzhengxu, et al.
Published: (2025)

WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment
by: Ou, Jiefu, et al.
Published: (2024)

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
by: Batra, Shourya, et al.
Published: (2025)