Cover Image

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shojaee, Parshin, Mirzadeh, Iman, Alizadeh, Keivan, Horton, Maxwell, Bengio, Samy, Farajtabar, Mehrdad
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
by: Mirzadeh, Iman, et al.
Published: (2024)

Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
by: Alizadeh, Keivan, et al.
Published: (2026)

LLM in a flash: Efficient Large Language Model Inference with Limited Memory
by: Alizadeh, Keivan, et al.
Published: (2023)

Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization
by: Samragh, Mohammad, et al.
Published: (2024)

Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
by: Lawsen, A.
Published: (2025)

Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity
by: Joudaki, Amir, et al.
Published: (2025)

SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
by: Chegini, Atoosa, et al.
Published: (2024)

Duo-LLM: A Framework for Studying Adaptive Computation in Large Language Models
by: Alizadeh, Keivan, et al.
Published: (2024)

Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection
by: Chegini, Atoosa, et al.
Published: (2025)

AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking
by: Gao, Silin, et al.
Published: (2025)

Computational Bottlenecks of Training Small-scale Large Language Models
by: Ashkboos, Saleh, et al.
Published: (2024)

TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining
by: Li, Jeffrey, et al.
Published: (2025)

LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers
by: Abhyankar, Nikhil, et al.
Published: (2025)

LLM-SR: Scientific Equation Discovery via Programming with Large Language Models
by: Shojaee, Parshin, et al.
Published: (2024)

Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges
by: Reddy, Chandan K, et al.
Published: (2024)

RL for Reasoning by Adaptively Revealing Rationales
by: Amani, Mohammad Hossein, et al.
Published: (2025)

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

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
by: Mehta, Sachin, et al.
Published: (2024)

OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
by: Mehta, Sachin, et al.
Published: (2024)

LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
by: Shojaee, Parshin, et al.
Published: (2025)

The Illusion of Insight in Reasoning Models
by: d'Aliberti, Liv G., et al.
Published: (2026)

A Comment On "The Illusion of Thinking": Reframing the Reasoning Cliff as an Agentic Gap
by: Khan, Sheraz, et al.
Published: (2025)

Thinking Isn't an Illusion: Overcoming the Limitations of Reasoning Models via Tool Augmentations
by: Song, Zhao, et al.
Published: (2025)

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
by: Maheswaran, Monishwaran, et al.
Published: (2025)

The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity
by: Chen, Yifang, et al.
Published: (2024)

Probing the "Psyche'' of Large Reasoning Models: Understanding Through a Human Lens
by: Chen, Yuxiang, et al.
Published: (2025)

Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning
by: Wang, Li, et al.
Published: (2025)

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

InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models
by: Yan, Yuchen, et al.
Published: (2025)

From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs
by: Nishu, Kumari, et al.
Published: (2025)

TIDE: Every Layer Knows the Token Beneath the Context
by: Jaiswal, Ajay, et al.
Published: (2026)

Understanding Inter-Session Intentions via Complex Logical Reasoning
by: Bai, Jiaxin, et al.
Published: (2023)

SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training
by: Meidani, Kazem, et al.
Published: (2023)

MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning
by: Tang, Xiangru, et al.
Published: (2025)

Federated Retrieval Augmented Generation for Multi-Product Question Answering
by: Shojaee, Parshin, et al.
Published: (2025)

Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models
by: Kim, Minseo, 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)

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

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

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