rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Paper
β’
2501.04519
β’
Published
β’
286
Reasoning π§
-
-
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though
Paper β’ 2501.04682 β’ Published β’ 99 -
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Paper β’ 2408.03314 β’ Published β’ 63 -
Training Large Language Models to Reason in a Continuous Latent Space
Paper β’ 2412.06769 β’ Published β’ 90 -
Test-time Computing: from System-1 Thinking to System-2 Thinking
Paper β’ 2501.02497 β’ Published β’ 46 -
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Paper β’ 2501.07301 β’ Published β’ 99 -
Evolving Deeper LLM Thinking
Paper β’ 2501.09891 β’ Published β’ 115 -
Hallucinations Can Improve Large Language Models in Drug Discovery
Paper β’ 2501.13824 β’ Published β’ 11 -
SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training
Paper β’ 2501.17161 β’ Published β’ 123 -
LIMO: Less is More for Reasoning
Paper β’ 2502.03387 β’ Published β’ 62 -
s1: Simple test-time scaling
Paper β’ 2501.19393 β’ Published β’ 124 -
The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding
Paper β’ 2502.08946 β’ Published β’ 193