AIME-2025

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

04:00

2026-08-20

arxiv.org

artificial-intelligence

Selection, Recombination, or a Fresh Solve? A Candidate-Free Control for Single-Pass Test-Time Aggregation

A new arXiv preprint (2608.18379v1) introduces a candidate-free control for single-pass test-time aggregation, finding that on AIME-2025 and HMMT-2025 with Qwen3-4B, conditioning on a candidate pool i…

04:13

2026-07-14

arxiv.org

artificial-intelligence

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Researchers introduce GEPA (Genetic-Pareto), a prompt optimizer that uses natural language reflection to learn from trial and error, outperforming reinforcement learning methods like GRPO by 6% on ave…

// co-occurs with top 6 entities

GEPA 1 GRPO 1 MIPROv2 1 arXiv 1 HMMT-2025 1 Qwen3-4B 1

// topics top 5 topics

artificial intelligence 2 large language models 2 ai research 2 ai tools 1 machine learning 1