AIBullisharXiv – CS AI · 4h ago7/10
🧠
Drawing on Memory: Dual-Trace Encoding Improves Cross-Session Recall in LLM Agents
Researchers introduce dual-trace memory encoding for LLM agents, pairing factual records with narrative scene reconstructions to improve cross-session recall by 20+ percentage points. The method significantly enhances temporal reasoning and multi-session knowledge aggregation without increasing computational costs, advancing the capability of persistent AI agent systems.