AIME

The AIME dataset/benchmark is used to evaluate the reasoning capabilities of large language models in the context of test-time scaling.

Papers using AIME (24)

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis2025 · 10 citesKimi k1.5: Scaling Reinforcement Learning with LLMs2025 · 11 citesWhen LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals2026KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling2026Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning2026Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling2026KVpop -- Key-Value Cache Compression with Predictive Online Pruning2026ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement2026Budget-Aware Anytime Reasoning with LLM-Synthesized Preference Data2026Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization2025Dr.LLM: Dynamic Layer Routing in LLMs2025MemLens: Uncovering Memorization in LLMs with Activation Trajectories2025Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-Tuning2025M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models2025LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling2025Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles2025Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs2025Efficient Reinforcement Finetuning via Adaptive Curriculum Learning2025Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought2025ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs2025Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning2025CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models2025From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs2025Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique2025