AI Briefing#aime
The latest AI and developer news about #aime, with the original source and a short summary.
The latest AI and developer news about #aime, with the original source and a short summary.
Self-organizing agent teams achieved 66.7% average accuracy across five benchmarks, surpassing the 59.0% achieved by a perfect router selecting the best individual member.
DeepSeek-R1-Lite-Preview showed o1-preview-level performance on AIME and MATH.