Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
Paper
• 2502.19361 • Published
• 28
reasoning
-
-
Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning
Paper • 2502.17407 • Published • 25 -
Small Models Struggle to Learn from Strong Reasoners
Paper • 2502.12143 • Published • 39 -
Language Models can Self-Improve at State-Value Estimation for Better Search
Paper • 2503.02878 • Published • 10 -
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
Paper • 2503.01307 • Published • 38 -
Chain of Draft: Thinking Faster by Writing Less
Paper • 2502.18600 • Published • 50 -
SoS1: O1 and R1-Like Reasoning LLMs are Sum-of-Square Solvers
Paper • 2502.20545 • Published • 22 -
LADDER: Self-Improving LLMs Through Recursive Problem Decomposition
Paper • 2503.00735 • Published • 23