BeyondAIME

BeyondAIME: Advancing Math Reasoning Evaluation Beyond High School Olympiads Dataset Description BeyondAIME is a curated test set designed to benchmark advanced mathematical reasoning. Its creation was guided by the following core principles to ensure a fair and challenging evaluation: High Difficulty: Problems are sou

Papers using BeyondAIME (6)

UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities2025 · 9 citesLearn Hard Problems During RL with Reference Guided Fine-tuning2026MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles2025Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models2026Evolutionary System Prompt Learning for Reinforcement Learning in LLMs2026