MinervaMath
Emerging5papers using it
2025first seen
The 'MinervaMath' dataset is a benchmark that contains mathematical problems used to evaluate the reasoning capabilities of large language models, particularly in the context of multi-step solutions and intermediate reasoning errors.
Papers using MinervaMath (5)
- CATPO: Critique-Augmented Tree Policy OptimizationLLM Reasoning with Process Rewards for Outcome-Guided StepsGRPO-$\lambda$: Credit Assignment improves LLM ReasoningWirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement LearningConfidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models