2 papers
cs.AI2026
Stable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression
Mingxuan Wang, Fei Luo, Bo Wang +6
Long horizon agents accumulate growing interaction histories that increase context and inference costs. We find that geometric redundancy alone is an insufficient criterion for saf…
cs.CV2026
AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI Navigation
Shengjie Jin, Zelong Sun, Hengbo Xu +2
Vision-Language Models (VLMs) enable autonomous GUI navigation, but agents still struggle to process and learn from dense, continuous visual histories. This bottleneck hinders both…