From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913099301257216 |
|---|---|
| author | Luo, Jinghao Tian, Yuchen Cao, Chuxue Luo, Ziyang Lin, Hongzhan Li, Kaixin Kong, Chuyi Yang, Ruichao Ma, Jing |
| author_facet | Luo, Jinghao Tian, Yuchen Cao, Chuxue Luo, Ziyang Lin, Hongzhan Li, Kaixin Kong, Chuyi Yang, Ruichao Ma, Jing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06716 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms Luo, Jinghao Tian, Yuchen Cao, Chuxue Luo, Ziyang Lin, Hongzhan Li, Kaixin Kong, Chuyi Yang, Ruichao Ma, Jing Artificial Intelligence Computation and Language 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. |
| title | From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.06716 |