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.AI2026
Memory Control Signals Emerge Before Action in Long Horizon Agents
Mingxuan Wang, Guorun Yao, Fei Luo +6
Long horizon language model agents continuously accumulate interaction history, increasing computational cost while making relevant information harder to preserve and reuse. Existi…