PlugMem: Transforming raw agent interactions into reusable knowledge
Ke Yang, Michel Galley, Chenglong Wang, Jianfeng Gao, Jiawei Han, ChengXiang Zhai
At a glance
- Today’s AI agents store long interaction histories but struggle to reuse them effectively.
- Raw memory retrieval can overwhelm agents with lengthy, low-value context.
- PlugMem transforms interaction history into structured, reusable knowledge.
- A single, general-purpose memory module improves performance across diverse agent benchmarks while using fewer memory tokens.
It seems counterintuitive: giving AI agents more memory can make them less effective. As interaction logs...