zjunlp/MobileMem

最近记录的来源活动: 2026年9月30日 08:00

SkillsMP 收录数据更新: 2026年11月2日 18:02

已收集 skills: 4

GitHub 星标: 32
GitHub Forks: 1

用 AI 助手安装

复制这段 Prompt，发给你正在使用的 AI 助手。

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/zjunlp/MobileMem.

仓库 README

仓库 README 来源：README.md

查看 README 源文件

展开完整 README

<div align="center"> <img src="omni/asset/logo.png" style="width: 50%; height: auto; box-shadow: 0 4px 18px rgba(0,0,0,0.06); display: block; margin: 0 auto;"> ### MobileMem: Learning from a Year of Mobile Experiences [![Technical Report](https://img.shields.io/badge/📄_Technical_Report-2608.13606v2-b31b1b?style=flat-square&logo=arxiv&logoColor=white)](https://arxiv.org/abs/2608.13606v2) [![Chinese Report](https://img.shields.io/badge/📄_Chinese_Report-202608.00183V1-ff6f00?style=flat-square&logo=googledocs&logoColor=white)](https://chinaxiv.org/abs/202608.00183V1) [![Website](https://img.shields.io/badge/🌐_Website-MobileMem-1e7bbf?style=flat-square&logo=googlechrome&logoColor=white)](https://zjunlp.github.io/MobileMem/) [![HuggingFace](https://img.shields.io/badge/🤗_Dataset-MobileMem-fcd022?style=flat-square)](https://huggingface.co/datasets/zjunlp/MobileMem) [![License](https://img.shields.io/badge/📜_License-MIT-2ea44f?style=flat-square&logo=opensourceinitiative&logoColor=white)](#license) --- <img src="omni/asset/fig1.png" style="width:100%; height: auto; border-radius: 14px; box-shadow: 0 4px 18px rgba(0,0,0,0.06);" align=center> **MobileMem** is a comprehensive benchmarking framework for evaluating **on-device memory systems** in realistic mobile environments. </div> --- ## 📑 Table of Contents - [📑 Table of Contents](#-table-of-contents) - [🔥 News](#-news) - [🎯 Applications](#-applications) - [📊 Dataset Structure](#-dataset-structure) - [🗂️ Project Structure](#️-project-structure) - [🚀 Getting Started](#-getting-started) - [📖 Text Track](#-text-track) - [🖼️ Omni Track](#️-omni-track) - [🧩 Struct Track](#-struct-track) - [🔍 Analyzing Failures with MemTrace](#-analyzing-failures-with-memtrace) - [🚩 Citation](#-citation) --- ## 🔥 News - **2026-09-30** — We released a structured Chinese version of the dataset and benchmark. - **2026-08-18** — We have officially released our [technical report](https://arxiv.org/abs/2608.13606v2). - **2026-08-01** — We publicly release the MobileMem dataset. - **2026-05-16** — We launch the English version of the dataset and benchmark. - **2026-05-03** — We launch the Chinese version of the dataset and benchmark. --- ## 🎯 Applications MobileMem is built from **multiple heterogeneous sources** to enable comprehensive on-device memory modeling. <img src="omni/asset/fig2.png" style="width:100%; height: auto; border-radius: 14px; box-shadow: 0 4px 18px rgba(0,0,0,0.06);" align=center> --- ## 📊 Dataset Structure MobileMem contains three complementary tracks: | Track | Modality | Description | | :--- | :--- | :--- | | **text** | Text | Long-horizon user–assistant conversations and structured mobile-app events for evaluating textual memory systems. | | **omni** | Text and images | Multimodal mobile interactions with screenshots and photos. | | **struct** | Structured data | Simulated structured data from on-device applications. | The dataset is available for download at [HuggingFace](https://huggingface.co/datasets/zjunlp/MobileMem). --- ## 🗂️ Project Structure The repository is organized into three main tracks. Track-specific details remain in each subdirectory. ```bash MobileMem/ │ ├── text/ # 📖 Text Track │ ├── README.md # Track-specific guide and dataset download │ ├── keme/ # 🛠️ KEME synthesis pipeline code │ └── eval/ # ⚙️ Evaluation scripts for text track │ ├── omni/ # 🖼️ Omni Track │ ├── README.md # Track-specific guide and dataset download │ ├── src/ # 🛠️ Data construction pipeline code │ └── eval/ # ⚙️ Evaluation scripts for omni track │ ├── struct/ # 🧩 Struct Track │ ├── README.md # Track-specific guide and dataset download │ ├── construct/ # 🛠️ Example generation and review (optional) │ └── eval/ # ⚙️ Evaluation for struct track │ └── README.md # This file ``` --- ## 🚀 Getting Started MobileMem offers three benchmark tracks. Choose the path that fits your needs and navigate to the corresponding resources. For an interactive visualization of the MobileMem data, visit the [Dataset Explorer](https://github.com/zjunlp/MobileMem/tree/Dataset-Explorer) branch. ### 📖 Text Track The textual benchmark for evaluating memory systems on long-term, knowledge-intensive mobile agent trajectories. | Section | Description | Quick Link | | :--- | :--- | :--- | | **📥 Data Access** | Download the synthesized KEME trajectories and QA pairs from HuggingFace. | [Link](https://huggingface.co/datasets/zjunlp/MobileMem) | | **⚙️ How to Evaluate** | **Detailed evaluation guide for reproducing leaderboard results is available in the [MemBase](https://github.com/zjunlp/MemBase/tree/main/examples/evaluate_memory_systems_on_mobilemem) repository.** | [Link](https://github.com/zjunlp/MemBase/tree/main/examples/evaluate_memory_systems_on_mobilemem) | | **🛠️ Data Construction** | Reproduce the KEME synthesis pipeline from scratch. | [Link](https://github.com/zjunlp/MobileMem/tree/main/text) | ### 🖼️ Omni Track The multimodal benchmark for evaluating on-device memory with realistic mobile images and dialogues. | Section | Description | Quick Link | | :--- | :--- | :--- | | **📥 Data Access** | Download the MobileMem-Omni dataset, including images and dialogues. | [Link](https://huggingface.co/datasets/zjunlp/MobileMem) | | **⚙️ How to Evaluate** | **Detailed evaluation guide for reproducing leaderboard results is available in the [MemBase](https://github.com/zjunlp/MemBase/tree/main/examples/evaluate_memory_systems_on_mobilemem_omni) repository.** | [Link](https://github.com/zjunlp/MemBase/tree/main/examples/evaluate_memory_systems_on_mobilemem_omni) | | **🛠️ Data Construction** | Rebuild the entire MobileMem-Omni dataset with the provided pipeline. | [Link](https://github.com/zjunlp/MobileMem/tree/main/omni) | ### 🧩 Struct Track Simulated structured data from on-device applications. | Section | Description | Quick Link | | :--- | :--- | :--- | | **📥 Data Access** | Download Struct cases and structured app records from HuggingFace. | [Link](https://huggingface.co/datasets/zjunlp/MobileMem) | | **⚙️ How to Evaluate** | Evaluate agent JSONL traces against Struct cases. | [Link](https://github.com/zjunlp/MobileMem/tree/main/struct) | | **🛠️ Data Construction** | Example generation and review Skills. | [Link](https://github.com/zjunlp/MobileMem/tree/main/struct/construct) | --- ## 🔍 Analyzing Failures with MemTrace We recommend using **[MemTrace](https://github.com/zjunlp/MemTrace)** to perform an in-depth error analysis. MemTrace helps you visualize and diagnose where and why your memory system fails, making it easier to pinpoint areas for improvement. For an example of how to use MemTrace, please refer to the [tutorial](https://github.com/zjunlp/MemBase/tree/main/examples/trace_memory_lifecycle_with_membase) in MemBase. --- ## 🚩 Citation If this work or datasets is helpful, please kindly cite as this: ```bibtex @techreport{mobilemem, title={MobileMem: Learning from a Year of Mobile Experiences}, author={Xinle Deng and Yida Xue and Xiangyuan Ru and Yijun Chen and Buqiang Xu and Mingjun Mao and Xinjie Liu and Haoming Xu and Shuofei Qiao and Mengru Wang and Chen Jiang and Yuchen Eleanor Jiang and Lizhong Wang and Jason Wang and Li Zeng and Haofen Wang and Guilin Qi and Huajun Chen and Ningyu Zhang}, year={2026}, institution={OPPO and OpenKG}, eprint={2608.13606}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/2608.13606}, } ```

正在加载仓库 README…

这个仓库中的 skills

职业分类待补全

skill

职业分类

描述

更新

case-construct

未分类

Construct memory-benchmark cases from persona-specific structured application data, including Queries, evidence, GT, gold answers, scoring, deductions, and scenario-aware safety or proactive behavior. Use when generating or substantially rewriting benchmark…

原文语言：英语

2026-09-30

case-review

未分类

Audit or repair existing memory-benchmark cases against persona-specific source data and the construction contract. Use for evidence verification, Query/GT/answer alignment, rubric checks, safety calibration, or case-file standardization; do not use merely to…

原文语言：英语

2026-09-30

data-construct

未分类

Construct or extend MobileMem Struct evidence data from a persona/event seed across bill, calendar, document, note, todo, voice, screen, and video sources. Use for evidence-corpus generation or substantial evidence rewrites; exclude image assets and benchmark…

原文语言：英语

2026-09-30

data-review

未分类

Audit or repair MobileMem Struct evidence data across event, bill, calendar, document, note, todo, voice, screen, and video sources. Use for schema, provenance, temporal, realism, or cross-record consistency checks; exclude image assets and benchmark cases.

原文语言：英语

2026-09-30

已展示 4 / 4 个已收集 Skill。