Updated October 18, 2026 · 56-page manuscript · Original figures & open reading resources
5Memory forms
4Lifecycle operations
4Platform families
215Cited works
32Benchmark entries
◇ THE LANDSCAPE
From personal experience to useful memory.
What should an agent remember, how should that memory change, and when should it shape an action? The survey connects these questions across five perspectives.
Figure 1-2. The survey taxonomy and representative works, reproduced from the latest manuscript.
◎ OVERVIEW · SECTIONS 1–2
SECTION 1 · INTRODUCTION
Memory, under everyday constraints.
Personal devices bring together continuous multimodal experience, bounded resources, and a user's long-term history. Useful agent memory must connect all three.
Explore the figure
Figure 1-1. Typical cloud and personal-device deployments across inputs, resource budgets, and personalization. Click any figure to enlarge ↗
This survey connects memory forms and lifecycle management to personalization, then examines deployment evidence, evaluation, and the challenges of sustained use on personal devices.
Agent memory keeps information from past observations, actions, and feedback available to the current decision process.
History→Memory→Action
Episodic
Specific experiences and the context in which they occurred.
Semantic
Facts and relationships usable beyond a single episode.
Procedural
Reusable skills and ways of carrying out an activity.
Short-term and long-term memory describe retention; working memory describes the active use of information in an ongoing task.
Local memory, within explicit limits
On-device agent memory is retained and processed on a personal device under resource budgets and data-use rules.
Peak runtime memory covers the agent as a whole: memory processing and model inference draw on the same available capacity.
Persistent storage preserves memory across interactions. Its budget limits the total storage footprint of the chosen system configuration.
Response time runs from receipt of a request to return of its result. Memory access and processing share this response budget with inference.
Energy includes both interactive processing and background maintenance over the period of operation. Moving maintenance off the response path still consumes energy.
Data-use rules
Specify what may be retained, for how long, and for which tasks. Later access, disclosure, correction, and deletion remain subject to user authorization.
01 MEMORY FORMS · SECTION 3
Five ways to retain experience.
A form defines the units in which memory is stored and reused. These forms can coexist: a personal fact, a reusable skill, and a repeated context need not share the same representation.
Explore the figure
Figure 3-1. Five memory forms and the subcategories used to organize the review.
EXPLICIT & INSPECTABLE
Textual memory
Selected experience is retained as natural language or structured text, making personal information available for direct inspection and revision.
CATEGORIES IN THE SURVEY
Event records
Hierarchical summaries
Task-state records
User profiles
Procedural experience
02 LIFECYCLE MANAGEMENT · SECTION 4
Memory is a process.
A memory store needs more than a write path. Its contents must enter tasks at the right time, incorporate new evidence, and leave when they are no longer useful or permitted.
01
Formation
Decide what enters memory, in which units, and with what provenance.
Admission · Units · Provenance02
Retrieval
Decide when to access memory, where to look, and how much evidence to return.
Triggering · Routing · Reduction03
Evolution
Consolidate jointly valid evidence and update facts or procedures as conditions change.
Consolidation · Updating04
Forgetting
Control continued residence and influence through selection, deletion, and unlearning.
Personal histories help an agent interpret preferences, resolve references, and anticipate needs. Privacy safeguards constrain how that history is retained and used throughout the system.
Explore the figure
Figure 5-1. Roles of personal memory and the privacy safeguards that constrain them.
PREFERENCES
What do I tend to choose?
Learn from explicit feedback and repeated behavior, while allowing preferences to change with context and time.
PERSONAL REFERENCES
What does this mean to me?
Link a request to the people, places, possessions, and experiences in a particular user's world.
PROACTIVE ASSISTANCE
Is this a useful moment to help?
Use recurring intent and present conditions to judge whether an intervention is timely and welcome.
04 ACROSS PLATFORMS · SECTION 6
Different devices. Different memory demands.
Four platform families connect memory design to the conditions in which agents operate. Device setting and execution location are examined separately.
PERSONAL COMPUTING
Phones & computers
Transient interface state, cross-application history, and local files support tasks that outlive a single screen.
Intermittent physiological, motion, and acoustic signals become event records and longer-term personal context.
SAMoSA · PHIA · MemPal
EMBODIED
Robots & simulated agents
Maps, object states, and reusable skills inform navigation and manipulation within perception–action loops.
VLONS · EfficientNav · Voyager
↳ A study's inclusion in a device context does not by itself establish end-to-end on-device execution. Section 6 distinguishes local components, remote computation, physical experiments, and simulation.
05 EVALUATION · SECTION 7
Measure what memory makes possible.
Evaluate information quality and useful behavior alongside the resources needed to sustain them.
01
Memory accuracy
Recall, evidence access, and reasoning over history.
02
Lifecycle effectiveness
Formation, updating, retention, and forgetting.
03
Personalization quality
User-specific interpretation and task outcomes.
04
On-device runtime cost
Memory footprint, latency, energy, and maintenance.
Benchmark explorer 32
General and device-context entries from Table 7-1.