MemDuet: Learning Dual-Process Memory for Long-Context Reasoning
Inspired by Kahneman's account of fast and slow thinking, MemDuet is a dual-process memory framework that learns to coordinate a small language model for fast, parallel evidence selection from raw context chunks with a large language model for memory-update verification and memory updates in document order.
Jiang-Cheng Song, Hao-Dong Jing, Yu-Ling Mu et al.
· 0 citations