标签: benchmarks - 66必读

12451v1 Announce Type: new Abstract: Large language models deployed as agents over large tool catalogs face a critical t

retrieval tool the

2026-06-12 Ashutosh Hathidara, Sai Shruthi Sistla, Sebastian Schreiber, Sahil Bansal

arXiv:2605.27379v1 Announce Type: new Abstract: We present Soro, a family of Tajik-specialized conversational large lang

Tajik and Soro

2026-05-28 Stanislav Liashkov, Haitz S\'aez de Oc\'ariz Borde, Azizjon Azimi, Khushbakht Shaymardonov, Shuhratjon Khalitbekov, Bonu Boboeva

12673v1 Announce Type: new Abstract: Agent benchmarks have become the de facto measure of frontier AI competence, guidin

the and benchmarks

2026-05-14 Hao Wang, Hanchen Li, Qiuyang Mang, Alvin Cheung, Koushik Sen, Dawn Song

#benchmarks