AIME 2024

AIME 2024 Dataset Dataset Description This dataset contains problems from the American Invitational Mathematics Examination (AIME) 2024. AIME is a prestigious high school mathematics competition known for its challenging mathematical problems. Dataset Details Format: JSONL Size: 30 records Source: AIME 2024 I & II Lang

Papers using AIME 2024 (27)

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space2025 · 26 citesCritique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback2025Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning2026Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention2025TEMPO: Scaling Test-time Training for Large Reasoning Models2026Robust Reasoning Benchmark2026Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation2026FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization2026Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation2025BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping2025Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty2025Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think2025Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier2025Prior Prompt Engineering for Reinforcement Fine-Tuning2025Not All Correct Answers Are Equal: Why Your Distillation Source Matters2025Self-Reflective Generation at Test Time2025DeepPrune: Parallel Scaling without Inter-trace Redundancy2025BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping2025LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!2025SIFT: Grounding LLM Reasoning in Contexts via Stickers2025TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation2025Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking2025Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space2025Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models2025Information-Preserving Reformulation of Reasoning Traces for Antidistillation2025Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention2025Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning2025