AIME-24

AIME 24 American Invitational Mathematics Examination (AIME) 2024 Citation If you use the AIME24 dataset in your research, please consider citing it as follows: @misc{aime24, title={American Invitational Mathematics Examination (AIME) 2024}, author={Zhang, Yifan and Math-AI, Team}, year={2024}, }

Papers using AIME-24 (36)

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation2025 · 25 citesSqueeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model2025 · 10 citesThinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners2025 · 4 citesMitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing2026Learn Hard Problems During RL with Reference Guided Fine-tuning2026Off-Policy Value-Based Reinforcement Learning for Large Language Models2026InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning2026iGRPO: Self-Feedback-Driven LLM Reasoning2026Latent Poincar\'e Shaping for Agentic Reinforcement Learning2026Long Chain-of-Thought Compression via Fine-Grained Group Policy Optimization2026Masked-and-Reordered Self-Supervision for Reinforcement Learning from Verifiable Rewards2025GRPO-$\lambda$: Credit Assignment improves LLM Reasoning2025Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward2025DCPO: Dynamic Clipping Policy Optimization2025SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning2025SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts2025Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention2025First Return, Entropy-Eliciting Explore2025SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM2025Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't2025Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement2024 · 12 citesBeyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning2025 · 1 citesLearn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning2025 · 1 citesProcess Reward Models That Think2025On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning2025Skywork Open Reasoner 1 Technical Report2025Promoting Efficient Reasoning with Verifiable Stepwise Reward2025Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation2025SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression2025Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning2025Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning2025Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning2025Prompt Augmentation Scales up GRPO Training on Mathematical Reasoning2026Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models2026SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling2026ASI-Evolve: AI Accelerates AI2026