Search papers, labs, and topics across Lattice.
University of Chineses Academy of Sciences
3
0
6
4
Skill augmentation can elevate CLI agent performance beyond GUI counterparts, revealing that the true challenge lies in skill coverage rather than model capability.
Models trained on the new VideoKR dataset achieve superior performance in knowledge-intensive video reasoning, setting a new benchmark for the field.
Standard retriever evaluations hide critical weaknesses in agentic search systems, but a new benchmark and training method exposes and addresses these flaws.
