A Comparative Study on Reasoning Patterns of OpenAI's o1 Model
Paper
•
2410.13639
•
Published
•
19
math
-
-
Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch
Paper • 2410.18693 • Published • 42 -
U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs
Paper • 2412.03205 • Published • 18 -
Free Process Rewards without Process Labels
Paper • 2412.01981 • Published • 34 -
ProcessBench: Identifying Process Errors in Mathematical Reasoning
Paper • 2412.06559 • Published • 84 -
BoostStep: Boosting mathematical capability of Large Language Models via improved single-step reasoning
Paper • 2501.03226 • Published • 44 -
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
Paper • 2412.21187 • Published • 40 -
The Lessons of Developing Process Reward Models in Mathematical Reasoning
Paper • 2501.07301 • Published • 99 -
MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning
Paper • 2510.14958 • Published • 22