Ceiling of a Task: When Can a Transformer Succeed Without Its Chain of Thought?
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- Reasoning Models Don't Always Say What They Think
- Implicit Chain of Thought Reasoning via Knowledge Distillation
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- Think before you speak: Training Language Models With Pause Tokens
- Non-Autoregressive Neural Machine Translation
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Training Large Language Models to Reason in a Continuous Latent Space
- Mercury: Ultra-Fast Language Models Based on Diffusion
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
- Let's Verify Step by Step
- Transformers Learn Shortcuts to Automata
- The Parallelism Tradeoff: Limitations of Log-Precision Transformers
- The Expressive Power of Transformers with Chain of Thought
- A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
- Large Language Diffusion Models
- Let's Think Dot by Dot: Hidden Computation in Transformer Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection