AMC

The 'AMC' dataset/benchmark contains a collection of mathematical reasoning problems used to evaluate the performance of large language models in solving multi-step mathematical tasks.

Papers using AMC (21)

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination2025 · 68 citesLogic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning2025 · 2 citesPrune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning2026LLM Reasoning with Process Rewards for Outcome-Guided Steps2026Tool Verification for Test-Time Reinforcement Learning2026PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning2026Boosting LLM Reasoning via Human-Inspired Reward Shaping2026Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis2026Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models2026TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning2025Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning2025ScRPO: From Errors to Insights2025GRPO-$\lambda$: Credit Assignment improves LLM Reasoning2025Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning2025Pinpointing crucial steps: Attribution-based Credit Assignment for Verifiable Reinforcement Learning2025CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections2025Inpainting-Guided Policy Optimization for Diffusion Large Language Models2025WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning2025Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention2025TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning2025Maximizing Confidence Alone Improves Reasoning2025