RESEARCH27
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
arXiv CS.AIΒ·May 11, 2026
Large Language Model (LLM)-based agents have reshaped artificial intelligence, yet research on memory mechanisms remains fragmented. This survey proposes a novel evolutionary framework for LLM agent memory mechanisms, formalizing the development process into three stages: Storage, Reflection, and Experience.
Read original β