Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction (2026)
HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents (2026)
Structured Episodic Event Memory (2026)
MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents (2026)
ES-Mem: Event Segmentation-Based Memory for Long-Term Dialogue Agents (2026)
Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents (2026)
CloneMem: Benchmarking Long-Term Memory for AI Clones (2026)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2026-01-15T01:38:27.971Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7132441997528076},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2601.04745","authors":[{"_id":"6964724e138cc47cbd765325","user":{"_id":"68e4ba9bb3738c567535654e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e4ba9bb3738c567535654e/DmkMgEaKb3N3bnbJYk1cC.png","isPro":false,"fullname":"wu","user":"realty2333","type":"user"},"name":"Tingyu Wu","status":"claimed_verified","statusLastChangedAt":"2026-01-14T09:53:39.763Z","hidden":false},{"_id":"6964724e138cc47cbd765326","user":{"_id":"692d850486aa9dfeebcf10b5","avatarUrl":"/avatars/6f7782844275f3eec7d8466fab787923.svg","isPro":false,"fullname":"Zhisheng Chen","user":"Zhisheng888","type":"user"},"name":"Zhisheng Chen","status":"admin_assigned","statusLastChangedAt":"2026-01-14T12:49:43.502Z","hidden":false},{"_id":"6964724e138cc47cbd765327","name":"Ziyan Weng","hidden":false},{"_id":"6964724e138cc47cbd765328","user":{"_id":"6776ce2f10eb0715dbb89df6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/GH7VYlzgdrUEDlQfW60Ez.png","isPro":false,"fullname":"Shuhe Wangv2","user":"Super-shuhe-v2","type":"user"},"name":"Shuhe Wang","status":"admin_assigned","statusLastChangedAt":"2026-01-14T12:49:52.050Z","hidden":false},{"_id":"6964724e138cc47cbd765329","user":{"_id":"6411c9c71d87842eedc5ad23","avatarUrl":"/avatars/b8a06aeafbbf7272a831534c2307d65e.svg","isPro":false,"fullname":"Chenglong Li","user":"ChenglongLi","type":"user"},"name":"Chenglong Li","status":"admin_assigned","statusLastChangedAt":"2026-01-14T12:49:57.344Z","hidden":false},{"_id":"6964724e138cc47cbd76532a","user":{"_id":"65562edfb7bad186e877c724","avatarUrl":"/avatars/bb91f42b102e113208bbe3238916a015.svg","isPro":false,"fullname":"zhangshuo","user":"mcflurryshuoz","type":"user"},"name":"Shuo Zhang","status":"claimed_verified","statusLastChangedAt":"2026-01-15T15:06:18.485Z","hidden":false},{"_id":"6964724e138cc47cbd76532b","name":"Sen Hu","hidden":false},{"_id":"6964724e138cc47cbd76532c","name":"Silin Wu","hidden":false},{"_id":"6964724e138cc47cbd76532d","user":{"_id":"68f287f2faba6f123f8a3b3c","avatarUrl":"/avatars/58a34b0f45bb34d74f86a638eff7dc94.svg","isPro":false,"fullname":"Qizhen Lan","user":"lanqz7766","type":"user"},"name":"Qizhen Lan","status":"admin_assigned","statusLastChangedAt":"2026-01-14T12:50:03.306Z","hidden":false},{"_id":"6964724e138cc47cbd76532e","user":{"_id":"6603d56ab4344a2b07cd6d21","avatarUrl":"/avatars/1569bb60166532317c85e80da722ba1c.svg","isPro":false,"fullname":"Huacan Wang","user":"Huacan-Wang","type":"user"},"name":"Huacan Wang","status":"admin_assigned","statusLastChangedAt":"2026-01-14T12:50:08.549Z","hidden":false},{"_id":"6964724e138cc47cbd76532f","user":{"_id":"6874f7f0f8e67e9b5714adf2","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/g2bltqJmCR7MY3zEaQHr6.png","isPro":false,"fullname":"RongHao Chen","user":"SuPA4ki","type":"user"},"name":"Ronghao Chen","status":"admin_assigned","statusLastChangedAt":"2026-01-14T12:50:13.928Z","hidden":false}],"publishedAt":"2026-01-08T09:11:33.000Z","submittedOnDailyAt":"2026-01-14T05:31:09.992Z","title":"KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions","submittedOnDailyBy":{"_id":"64084fa192033c150738e4f2","avatarUrl":"/avatars/dfff2216eb235c635e5abe6fda3084f0.svg","isPro":false,"fullname":"Yu_xm","user":"Yu2020","type":"user"},"summary":"Existing long-horizon memory benchmarks mostly use multi-turn dialogues or synthetic user histories, which makes retrieval performance an imperfect proxy for person understanding. We present \\BenchName, a publicly releasable benchmark built from long-form autobiographical narratives, where actions, context, and inner thoughts provide dense evidence for inferring stable motivations and decision principles. \\BenchName~reconstructs each narrative into a flashback-aware, time-anchored stream and evaluates models with evidence-linked questions spanning factual recall, subjective state attribution, and principle-level reasoning. Across diverse narrative sources, retrieval-augmented systems mainly improve factual accuracy, while errors persist on temporally grounded explanations and higher-level inferences, highlighting the need for memory mechanisms beyond retrieval. Our data is in KnowMeBench{https://github.com/QuantaAlpha/KnowMeBench}.","upvotes":58,"discussionId":"6964724f138cc47cbd765330","githubRepo":"https://github.com/QuantaAlpha/KnowMeBench","githubRepoAddedBy":"user","ai_summary":"Long-horizon memory benchmarks based on autobiographical narratives evaluate models' ability to infer stable motivations and decision principles through evidence-linked questions spanning factual recall, subjective state attribution, and principle-level reasoning.","ai_keywords":["memory benchmarks","autobiographical narratives","retrieval-augmented systems","factual recall","subjective state attribution","principle-level reasoning"],"githubStars":117,"organization":{"_id":"68b33ab6a9ed99140481cf44","name":"QuantaAlpha","fullname":"QuantaAlpha","avatar":"https://cdn-uploads.huggingface.co/production/uploads/63f7767fbd28622c9b9915e9/DRN8PvmnpKmn2MSLQ7qhF.jpeg"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"66a0ab4923e426e19db92773","avatarUrl":"/avatars/19517dd085a3e48e644613ca0b2c3753.svg","isPro":false,"fullname":"ronghaochen","user":"cristiano28","type":"user"},{"_id":"692881094c3f4293dfe29e3d","avatarUrl":"/avatars/bddfaae8041a45498d46ef65ba17c920.svg","isPro":false,"fullname":"qihao wang","user":"jimson991","type":"user"},{"_id":"671b8b4d2eeb8de1c153aaa4","avatarUrl":"/avatars/9d11e80e79e817e01d2d7a032b186b98.svg","isPro":false,"fullname":"Xiaoba","user":"Xiaoba123","type":"user"},{"_id":"66260fa6eb729227ec6c002a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66260fa6eb729227ec6c002a/bwhhv6xkP7M9YbCOXDpp1.jpeg","isPro":false,"fullname":"Heng Lian","user":"Pixelieee","type":"user"},{"_id":"692d850486aa9dfeebcf10b5","avatarUrl":"/avatars/6f7782844275f3eec7d8466fab787923.svg","isPro":false,"fullname":"Zhisheng Chen","user":"Zhisheng888","type":"user"},{"_id":"662911a202f5ad9a5195932f","avatarUrl":"/avatars/3c7db9bf9c1d95360b62fe4f56ee9c3a.svg","isPro":false,"fullname":"Tu Hu","user":"Blackteaxxx","type":"user"},{"_id":"64084fa192033c150738e4f2","avatarUrl":"/avatars/dfff2216eb235c635e5abe6fda3084f0.svg","isPro":false,"fullname":"Yu_xm","user":"Yu2020","type":"user"},{"_id":"68e4ba9bb3738c567535654e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/68e4ba9bb3738c567535654e/DmkMgEaKb3N3bnbJYk1cC.png","isPro":false,"fullname":"wu","user":"realty2333","type":"user"},{"_id":"676e3120aeae4cac1577daeb","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/i_xUSDbzbxPPB9rSqs1eV.png","isPro":false,"fullname":"zhengzhenkun","user":"akun-bupt","type":"user"},{"_id":"67c08207cd6b906a0d03a39b","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/67c08207cd6b906a0d03a39b/hBnoZ8soyF9BSlU7AgH14.jpeg","isPro":false,"fullname":"AbstractionLayer","user":"SatoHaruto","type":"user"},{"_id":"67b18f3836b9713b3e09e015","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/67b18f3836b9713b3e09e015/njQNs9VF05MQvySDX6yg1.png","isPro":false,"fullname":"haiy bai","user":"Warsun","type":"user"},{"_id":"67b0a2d9e2883deef7246748","avatarUrl":"/avatars/4a478f37b6e605cb9cf806b4558121fa.svg","isPro":false,"fullname":"Hyunwoo","user":"CHyunwoo","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0,"organization":{"_id":"68b33ab6a9ed99140481cf44","name":"QuantaAlpha","fullname":"QuantaAlpha","avatar":"https://cdn-uploads.huggingface.co/production/uploads/63f7767fbd28622c9b9915e9/DRN8PvmnpKmn2MSLQ7qhF.jpeg"}}">

Papers

arxiv:2601.04745

KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions

Published on Jan 8

· Submitted by

Yu_xm on Jan 14

QuantaAlpha

Upvote

Authors:

Tingyu Wu ,

Zhisheng Chen ,

Shuhe Wang ,

Chenglong Li ,

Shuo Zhang ,

Qizhen Lan ,

Huacan Wang ,

Ronghao Chen

Abstract

Long-horizon memory benchmarks based on autobiographical narratives evaluate models' ability to infer stable motivations and decision principles through evidence-linked questions spanning factual recall, subjective state attribution, and principle-level reasoning.

AI-generated summary

Existing long-horizon memory benchmarks mostly use multi-turn dialogues or synthetic user histories, which makes retrieval performance an imperfect proxy for person understanding. We present \BenchName, a publicly releasable benchmark built from long-form autobiographical narratives, where actions, context, and inner thoughts provide dense evidence for inferring stable motivations and decision principles. \BenchName~reconstructs each narrative into a flashback-aware, time-anchored stream and evaluates models with evidence-linked questions spanning factual recall, subjective state attribution, and principle-level reasoning. Across diverse narrative sources, retrieval-augmented systems mainly improve factual accuracy, while errors persist on temporally grounded explanations and higher-level inferences, highlighting the need for memory mechanisms beyond retrieval. Our data is in KnowMeBench{https://github.com/QuantaAlpha/KnowMeBench}.