Hugging Face Daily Papers · August 17, 2026 · 3 min read

MobileMem: Learning from a Year of Mobile Experiences

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

Like Read original ↗

MobileMem, a benchmark and framework for studying on-device long-term memory, grounded in a year-scale collection of mobile experiences.</p>\n","updatedAt":"2026-08-17T04:08:51.401Z","author":{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","fullname":"Ningyu Zhang","name":"Ningyu","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":55,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8466261029243469},"editors":["Ningyu"],"editorAvatarUrls":["/avatars/e0fccbb2577d76088e09f054c35cffbc.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2608.13606","authors":[{"_id":"6a82709fb601d59c652813ea","name":"Xinle Deng","hidden":false},{"_id":"6a82709fb601d59c652813eb","name":"Yida Xue","hidden":false},{"_id":"6a82709fb601d59c652813ec","name":"Xiangyuan Ru","hidden":false},{"_id":"6a82709fb601d59c652813ed","name":"Haoming Xu","hidden":false},{"_id":"6a82709fb601d59c652813ee","name":"Shuofei Qiao","hidden":false},{"_id":"6a82709fb601d59c652813ef","name":"Mengru Wang","hidden":false},{"_id":"6a82709fb601d59c652813f0","name":"Yijun Chen","hidden":false},{"_id":"6a82709fb601d59c652813f1","name":"Buqiang Xu","hidden":false},{"_id":"6a82709fb601d59c652813f2","name":"Chen Jiang","hidden":false},{"_id":"6a82709fb601d59c652813f3","name":"Yuchen Eleanor Jiang","hidden":false},{"_id":"6a82709fb601d59c652813f4","name":"Lizhong Wang","hidden":false},{"_id":"6a82709fb601d59c652813f5","name":"Jianfeng Wang","hidden":false},{"_id":"6a82709fb601d59c652813f6","name":"Li Zeng","hidden":false},{"_id":"6a82709fb601d59c652813f7","name":"Haofen Wang","hidden":false},{"_id":"6a82709fb601d59c652813f8","name":"Guilin Qi","hidden":false},{"_id":"6a82709fb601d59c652813f9","name":"Huajun Chen","hidden":false},{"_id":"6a82709fb601d59c652813fa","name":"Ningyu Zhang","hidden":false}],"publishedAt":"2026-08-11T00:00:00.000Z","submittedOnDailyAt":"2026-08-17T00:00:00.000Z","title":"MobileMem: Learning from a Year of Mobile Experiences","submittedOnDailyBy":{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","isPro":true,"fullname":"Ningyu Zhang","user":"Ningyu","type":"user","name":"Ningyu"},"summary":"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.","upvotes":16,"discussionId":"6a82709fb601d59c652813fb","projectPage":"https://zjunlp.github.io/MobileMem/","githubRepo":"https://github.com/zjunlp/MobileMem","githubRepoAddedBy":"user","ai_summary":"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.","ai_keywords":["on-device long-term memory","multimodal","knowledge-grounded synthesis","multi-hop reasoning","temporal reasoning","implicit preference inference","experiential intelligence"],"ai_summary_model":"thinkingmachines/Inkling-Small","githubStars":11,"organization":{"_id":"64931391a174fb4371dc5c63","name":"openkg","fullname":"OpenKG Consortium","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/64931296137833d7ec7689cd/QqZVrBDayak-COt40aVd6.jpeg"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","isPro":true,"fullname":"Ningyu Zhang","user":"Ningyu","type":"user"},{"_id":"6a423becb8d5b1993fe57107","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6a423becb8d5b1993fe57107/Oz6-_wGMeyelTX8Qq7Mzo.jpeg","isPro":false,"fullname":"Yenan Wang","user":"crepuscular-drizzle","type":"user"},{"_id":"684bc1be17ae31ba66171292","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/684bc1be17ae31ba66171292/LFlkU4kArMjSzIbwjXd44.jpeg","isPro":false,"fullname":"Jingsheng Zheng","user":"JohnsonZheng03","type":"user"},{"_id":"65cad52fd6c974694fc20b8e","avatarUrl":"/avatars/8232a7c5db590ed26751a47c45d481b8.svg","isPro":false,"fullname":"Xinle Deng","user":"Linear-Matrix-Probability","type":"user"},{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"},{"_id":"68d8fc00ff474874c83a1c99","avatarUrl":"/avatars/17e3a2f5197274536bf68d949c5416db.svg","isPro":false,"fullname":"huminclu","user":"huminclu","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"63f89fe7565506a9cadcd2cf","avatarUrl":"/avatars/7eb449a1109dcff051cb3ba680f0c082.svg","isPro":false,"fullname":"Jintian Zhang","user":"MikeDean","type":"user"},{"_id":"6a1443f02a9759cfbdf80a48","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6a1443f02a9759cfbdf80a48/dIoHGMzJ3U6k7VTOaBd4Y.jpeg","isPro":false,"fullname":"Haoxiong Wang","user":"WangHX2026","type":"user"},{"_id":"6639c1831d39aa6896f7e2fd","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6639c1831d39aa6896f7e2fd/aburVZ0k7K-TjfVQIHERI.jpeg","isPro":false,"fullname":"Rui Hu","user":"Raynhu","type":"user"},{"_id":"679b6d152583e6629337c592","avatarUrl":"/avatars/7ad77d7384fd41ad987b6eb5907a8f08.svg","isPro":false,"fullname":"Yuqi","user":"Yukirsh","type":"user"},{"_id":"6437871ecd93f4c9a34dcef1","avatarUrl":"/avatars/ef333b726c55fbed469d6f10b62aad58.svg","isPro":false,"fullname":"Lethe","user":"ethe","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"64931391a174fb4371dc5c63","name":"openkg","fullname":"OpenKG Consortium","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/64931296137833d7ec7689cd/QqZVrBDayak-COt40aVd6.jpeg"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2608/2608.13606.md","query":{}}">

Papers

arxiv:2608.13606

MobileMem: Learning from a Year of Mobile Experiences

Published on Aug 11

· Submitted by

Ningyu Zhang on Aug 17

OpenKG Consortium

Upvote

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.

Generated by thinkingmachines/Inkling-Small

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.