Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Memory as Asset: From Agent-centric to Human-centric Memory Management

Yanqi Pan, Qinghao Huang, Weihao Yang

Abstract

We proudly introduce Memory-as-Asset, a new memory paradigm towards human-centric artificial general intelligence (AGI). In this paper, we formally emphasize that human-centric, personal memory management is a prerequisite for complementing the collective knowledge of existing large language models (LLMs) and extending their knowledge boundaries through self-evolution. We introduce three key features that shape the Memory-as-Asset era: (1) Memory in Hand, which emphasizes human-centric ownership to maximize benefits to humans; (2) Memory Group, which provides collaborative knowledge formation to avoid memory islands, and (3) Collective Memory Evolution, which enables continuous knowledge growth to extend the boundary of knowledge towards AGI. We finally give a potential three-layer memory infrastructure to facilitate the Memory-as-Asset paradigm, with fast personal memory storage, an intelligent evolution layer, and a decentralized memory exchange network. Together, these components outline a foundational architecture in which personal memories become persistent digital assets that can be accumulated, shared, and evolved over time. We believe this paradigm provides a promising path toward scalable, human-centric AGI systems that continuously grow through the collective experiences of individuals and intelligent agents.

Memory as Asset: From Agent-centric to Human-centric Memory Management

Abstract

We proudly introduce Memory-as-Asset, a new memory paradigm towards human-centric artificial general intelligence (AGI). In this paper, we formally emphasize that human-centric, personal memory management is a prerequisite for complementing the collective knowledge of existing large language models (LLMs) and extending their knowledge boundaries through self-evolution. We introduce three key features that shape the Memory-as-Asset era: (1) Memory in Hand, which emphasizes human-centric ownership to maximize benefits to humans; (2) Memory Group, which provides collaborative knowledge formation to avoid memory islands, and (3) Collective Memory Evolution, which enables continuous knowledge growth to extend the boundary of knowledge towards AGI. We finally give a potential three-layer memory infrastructure to facilitate the Memory-as-Asset paradigm, with fast personal memory storage, an intelligent evolution layer, and a decentralized memory exchange network. Together, these components outline a foundational architecture in which personal memories become persistent digital assets that can be accumulated, shared, and evolved over time. We believe this paradigm provides a promising path toward scalable, human-centric AGI systems that continuously grow through the collective experiences of individuals and intelligent agents.
Paper Structure (36 sections, 16 equations, 1 figure)

This paper contains 36 sections, 16 equations, 1 figure.

Table of Contents

  1. Introduction
  2. Local memory systems.
  3. Centralized memory systems.
  4. Decentralized memory systems.
  5. Related Work
  6. LLM in the Wild: Agents With No Memory
  7. Agents With Local Memory
  8. Centralized Memory Systems
  9. Decentralized Memory Systems
  10. Summary
  11. Motivation: Human-Centric Memory for Knowledge Evolution
  12. Memory and Knowledge Representation
  13. Types of Knowledge and Memory Representation
  14. Human-Centric Knowledge Filtering
  15. Memory Evolution
  16. ...and 21 more sections

Figures (1)

  • Figure 1: Architecture of the Memory as Asset System (MAS). The outer ring represents the decentralized Personal Storage Layer, where each group maintains a personal memory space consisting of multiple personal agents. Each group connects to a local evolution node forming the Evolution Layer, responsible for updating the memory space through interaction-driven evolution. At the center lies the Memory Exchange network, which enables decentralized discovery and exchange of memory assets. The crossed symbols in the core represent the underlying network fabric supporting distributed memory exchange.