AIBullisharXiv – CS AI · Mar 36/1010
🧠
Efficient Long-Horizon GUI Agents via Training-Free KV Cache Compression
Researchers developed ST-Lite, a training-free KV cache compression framework that accelerates GUI agents by 2.45x while using only 10-20% of the cache budget. The solution addresses memory and latency constraints in Vision-Language Models for autonomous GUI interactions through specialized attention pattern optimization.