Search papers, labs, and topics across Lattice.
2
0
5
2
Web agents can actually get *more* efficient as they learn, achieving state-of-the-art performance with significantly fewer tokens via online skill distillation.
LLMs can maintain near-perfect long-context recall (91.4% on Needle-in-a-Haystack) while slashing memory use by intelligently pruning the KV cache based on the model's own confidence.
