MobileMem: Learning from a Year of Mobile Experiences

Hugging Face Daily Papers Papers
on-device-ai long-term-memory multimodal temporal-reasoning benchmark

Summary

MobileMem introduces a benchmark and framework for on-device AI systems to learn from year-long mobile experiences, focusing on temporal reasoning, knowledge updating, and preference inference.

The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users' experiences. Such assistants require long-term memory to accumulate and leverage user-specific experiences over time, yet existing benchmarks remain inadequate for realistic mobile settings, where experiences are heterogeneous, multimodal, evolving, and deeply personal. We introduce MobileMem, a benchmark and framework for studying on-device long-term memory, grounded in a year-scale collection of mobile experiences. MobileMem employs a knowledge-grounded synthesis pipeline to construct coherent and temporally consistent long-horizon trajectories from user-app sessions. It provides complementary text and multimodal settings covering multi-hop and temporal reasoning, knowledge updating, and implicit preference inference. Specifically, MobileMem enables agents to remember the past, understand the present, and adapt to the future. By modeling experiences rather than isolated facts, MobileMem moves memory beyond information retrieval toward experiential intelligence for continuous personal learning.
Original Article
View Cached Full Text

Cached at: 08/17/26, 07:46 AM

Paper page - MobileMem: Learning from a Year of Mobile Experiences

Source: https://huggingface.co/papers/2608.13606 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

MobileMem is a benchmark and framework for evaluating on-device long-term memory through year-scale, multimodal mobile experience trajectories that require temporal reasoning, knowledge updating, and preference inference.

The next generation of AI agents is increasingly moving beyond systems that answer isolated questions toward persistent personal assistants that can understand, remember, and continuously learn from users’ experiences. Such assistants require long-term memory to accumulate and leverage user-specific experiences over time, yet existing benchmarks remain inadequate for realistic mobile settings, where experiences are heterogeneous,multimodal, evolving, and deeply personal. We introduce MobileMem, a benchmark and framework for studyingon-device long-term memory, grounded in a year-scale collection of mobile experiences. MobileMem employs aknowledge-grounded synthesispipeline to construct coherent and temporally consistent long-horizon trajectories from user-app sessions. It provides complementary text andmultimodalsettings covering multi-hop andtemporal reasoning, knowledge updating, andimplicit preference inference. Specifically, MobileMem enables agents to remember the past, understand the present, and adapt to the future. By modeling experiences rather than isolated facts, MobileMem moves memory beyond information retrieval towardexperiential intelligencefor continuous personal learning.

View arXiv pageView PDFProject pageGitHub11Add to collection

Get this paper in your agent:

hf papers read 2608\.13606

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.13606 in a model README.md to link it from this page.

Datasets citing this paper1

#### zjunlp/MobileMem Updatedabout 5 hours ago • 224 • 2

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.13606 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents

arXiv cs.AI

The article introduces MindMemOS, a portable and self-evolving memory operating layer for AI agents that uses a unified entity-property-time structure, with algorithms for memory refinement and skill evolution. It achieves notable accuracy on LOCOMO and PersonaMem benchmarks and improves SpreadsheetBench performance by 9.2 percentage points.

MemArena: An Ego-Centric Benchmark for On-Device Agentic Personal Memory Assistants at Scale

arXiv cs.CL

MemArena is a new ego-centric benchmark for evaluating on-device personal memory assistants, using a MASim agent simulator to generate multi-session conversational worlds and ground truth across recall, reasoning, and trustworthiness dimensions. Initial results show memory-backend choice often matters more than reader scale, and permission-aware access remains a universal challenge.

MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories

Hugging Face Daily Papers

MemLife introduces a multimodal memory system for long-term egocentric videos that builds entity-grounded text episodes and retrieves them with a time-indexed agentic reader, improving over training-free baselines by 4.6-12.0% on long-horizon benchmarks. A reinforcement learning framework called MemOpt further optimizes the memory writer for faithfulness and retrievability, yielding consistent 2.7-5.0% gains.

Learning to Learn from Multimodal Experience

arXiv cs.AI

This paper introduces AutoMMemo, a framework that enables multimodal agents to automatically design memory mechanisms (expressible as executable memo programs) for learning from multimodal interaction trajectories, outperforming no-memory and fixed-memory baselines on GUI/Web navigation and visual reasoning benchmarks.

SelfMem: Self-Optimizing Memory for AI Agents

arXiv cs.CL

SelfMem introduces a self-optimizing memory framework for AI agents that allows them to explore, evaluate, and refine their own memory strategies through memory tools and feedback signals, achieving significant improvements over baselines on the BEAM benchmark across large conversation scales.