#MLE-bench

2 stories · 0 in 7 days · 1 in 30 days

Stories, products and papers tagged "MLE-bench", newest first.

10月12日

两个智能体轮流干、每次重置上下文，Kaggle 奖牌率干到 78.2%，还只用基线四分之一时间，做 MLE 智能体的可以细看。

arXiv cs.AI@Changye Li et al. (15)Source

9月3日

Models BuildersSelected73°12:16

This approach improves AI research efficiency by converting open-source code into reusable skills that boost performance across multiple benchmarks.

arXiv cs.AI@Jianlyu Chen et al. (11)Source