AIME 2024
Emerging23papers using it
36,217HF downloads
83HF likes
2025first seen
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
🤗 Hugging Face⚖ mit
Papers using AIME 2024 (23)
- Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent SpaceCritique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical FeedbackDistribution-Aware Reward Estimation for Test-Time Reinforcement LearningLess is More: Improving LLM Reasoning with Minimal Test-Time InterventionBAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive ClippingPrompting Test-Time Scaling Is A Strong LLM Reasoning Data AugmentationFast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length PenaltyBAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via
Balanced Policy Optimization with Adaptive ClippingLLMs Can Easily Learn to Reason from Demonstrations Structure, not
content, is what matters!SIFT: Grounding LLM Reasoning in Contexts via StickersTinyR1-32B-Preview: Boosting Accuracy with Branch-Merge DistillationThink Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time
ThinkingBeyond the Last Answer: Your Reasoning Trace Uncovers More than You
ThinkSolve-Detect-Verify: Inference-Time Scaling with Flexible Generative
VerifierSeek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient
in Latent SpacePrior Prompt Engineering for Reinforcement Fine-TuningNot All Correct Answers Are Equal: Why Your Distillation Source MattersConfidence Is All You Need: Few-Shot RL Fine-Tuning of Language ModelsSelf-Reflective Generation at Test TimeDeepPrune: Parallel Scaling without Inter-trace RedundancyInformation-Preserving Reformulation of Reasoning Traces for
AntidistillationLess is More: Improving LLM Reasoning with Minimal Test-Time
InterventionWalk Before You Run! Concise LLM Reasoning via Reinforcement Learning