AIME

The AIME dataset/benchmark contains mathematical reasoning tasks used to evaluate the performance of large language models in generating correct solutions and intermediate reasoning steps.

Papers using AIME (33)

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination2025 · 68 citesCDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models2025 · 26 citesKimi k1.5: Scaling Reinforcement Learning with LLMs2025 · 11 citesRing-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs2025Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL2026Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning2025 · 2 citesVariational Proximal Policy Optimization2026PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR2026Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning2026LLM Reasoning with Process Rewards for Outcome-Guided Steps2026Latent-GRPO: Group Relative Policy Optimization for Latent Reasoning2026Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models2026Boosting LLM Reasoning via Human-Inspired Reward Shaping2026EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization2026Evolutionary System Prompt Learning for Reinforcement Learning in LLMs2026ETR: Outcome-Guided Elastic Trust Regions for Policy Optimization2026SD-E$^2$: Semantic Exploration for Reasoning Under Token Budgets2026Long-horizon Reasoning Agent for Olympiad-Level Mathematical Problem Solving2025ScRPO: From Errors to Insights2025h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning2025Pinpointing crucial steps: Attribution-based Credit Assignment for Verifiable Reinforcement Learning2025MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs2025CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections2025GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA2025Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning2025WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning2025Reward Is Enough: LLMs Are In-Context Reinforcement Learners2025RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning2025TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning2025On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles2025Maximizing Confidence Alone Improves Reasoning2025DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition2025