Hongzhan Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Hongzhan Lin has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chuxue Cao
Hong Kong University of Science and Technology, Hong Kong
1 shared publication - Chuyi Kong
Hong Kong Baptist University, Hong Kong
1 shared publication - Jing Ma
Hong Kong Baptist University, Hong Kong, Hong Kong
1 shared publication - Jinghao Luo
South China Normal University, China
1 shared publication - Kaixin Li
National University of Singapore, Singapore
1 shared publication - Ruichao Yang
University of Science and Technology Beijing, China
1 shared publication
Latest Publications
- Open Access
- 15 January 2026
- Published by MDPI AG in Preprints.org
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
Large Language Model (LLM)-based agents have fundamentally reshaped artificial intelligence by integrating external tools and planning capabilities. While memory mechanisms have emerged as the architectural cornerstone of these systems, current research remains fragmented, oscillating between operating system engineering and cognitive science. This theoretical divide prevents a unified view of technological synthesis and a coherent evolutionary perspective. To bridge this gap, this survey proposes a novel evolutionary framework for LLM agent memory mechanisms, formalizing the development process into three stages: Storage (trajectory preservation), Reflection (trajectory refinement), and Experience (trajectory abstraction). We first formally define these three stages before analyzing the three core drivers of this evolution: the necessity for long-range consistency, the challenges in dynamic environments, and the ultimate goal of continual learning. Furthermore, we specifically explore two transformative mechanisms in the frontier Experience stage: proactive exploration and cross-trajectory abstraction. By synthesizing these disparate views, this work offers robust design principles and a clear roadmap for the development of next-generation LLM agents.
- 15 January 2026
- Published by MDPI AG in Preprints.org
Open AccessFrom Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
Large Language Model (LLM)-based agents have fundamentally reshaped artificial intelligence by integrating external tools and planning capabilities. While memory mechanisms have emerged as the architectural cornerstone of these systems, current research remains fragmented, oscillating between operating system engineering and cognitive science. This theoretical divide prevents a unified view of technological synthesis and a coherent evolutionary perspective. To bridge this gap, this survey proposes a novel evolutionary framework for LLM agent memory mechanisms, formalizing the development process into three stages: Storage (trajectory preservation), Reflection (trajectory refinement), and Experience (trajectory abstraction). We first formally define these three stages before analyzing the three core drivers of this evolution: the necessity for long-range consistency, the challenges in dynamic environments, and the ultimate goal of continual learning. Furthermore, we specifically explore two transformative mechanisms in the frontier Experience stage: proactive exploration and cross-trajectory abstraction. By synthesizing these disparate views, this work offers robust design principles and a clear roadmap for the development of next-generation LLM agents.