Hugging Face Daily Papers · June 17, 2026 · 4 min read

LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

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

Like Read original ↗

Effective personalized AI-assisted learning demands learning systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. LectūraAgents is here to address such needs.</p>\n","updatedAt":"2026-06-17T01:53:11.718Z","author":{"_id":"61e52be53d6dbb1da842316a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61e52be53d6dbb1da842316a/gx0WGPcOCClXPymoKglc4.jpeg","fullname":"Börje Karlsson","name":"tellarin","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":29,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.9455208778381348},"editors":["tellarin"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/61e52be53d6dbb1da842316a/gx0WGPcOCClXPymoKglc4.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.16428","authors":[{"_id":"6a31fd85bc818ff14e453cea","user":{"_id":"6438a9027de34e8ea7e4b257","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6438a9027de34e8ea7e4b257/vib8QSd1AWMr_bR9ig_xJ.jpeg","isPro":false,"fullname":"Jaward Sesay","user":"Jaward","type":"user","name":"Jaward"},"name":"Jaward Sesay","status":"claimed_verified","statusLastChangedAt":"2026-06-17T11:21:19.522Z","hidden":false},{"_id":"6a31fd85bc818ff14e453ceb","name":"Yue Yu","hidden":false},{"_id":"6a31fd85bc818ff14e453cec","name":"Siwei Dong","hidden":false},{"_id":"6a31fd85bc818ff14e453ced","name":"Yemin Shi","hidden":false},{"_id":"6a31fd85bc818ff14e453cee","name":"Guangyao Chen","hidden":false},{"_id":"6a31fd85bc818ff14e453cef","user":{"_id":"61e52be53d6dbb1da842316a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61e52be53d6dbb1da842316a/gx0WGPcOCClXPymoKglc4.jpeg","isPro":false,"fullname":"Börje Karlsson","user":"tellarin","type":"user","name":"tellarin"},"name":"Börje F. Karlsson","status":"claimed_verified","statusLastChangedAt":"2026-06-17T11:21:21.583Z","hidden":false}],"publishedAt":"2026-06-15T00:00:00.000Z","submittedOnDailyAt":"2026-06-17T00:00:00.000Z","title":"LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching","submittedOnDailyBy":{"_id":"61e52be53d6dbb1da842316a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61e52be53d6dbb1da842316a/gx0WGPcOCClXPymoKglc4.jpeg","isPro":false,"fullname":"Börje Karlsson","user":"tellarin","type":"user","name":"tellarin"},"summary":"Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. However, existing educational agents have primarily focused on lecture content automation and simulations, which often fall short of modelling multimodal and embodied instructional methods tailored for the individual learner. To this end, we propose LectūraAgents - a multi-agent framework that enables personalized learning through end-to-end adaptive embodied teaching. At its core, LectūraAgents mirrors a professor-student relationship, in which a ProfessorAgent leads a collaborative team of specialized subordinate agents through research, planning, review, and embodied delivery of lecture contents that adapt to a learner's needs. The framework offers three main contributions: (1) a hierarchical multi-agent architecture for end-to-end personalized learning; (2) an adaptive embodied teaching mechanism, wherein the ProfessorAgent executes visible and pedagogically motivated teaching actions (e.g., handwrite, highlight, underline, etc.) over contents in a teaching environment; and (3) a Teaching Action-Speech Alignment (TASA) algorithm that employs salience-based heuristics and temporal semantic segmentation to generate coherent teaching action sequences aligned with learner profiles. We evaluate LectūraAgents on diverse courses at high school, undergraduate, and graduate levels using sample-specific rubric-based analysis; with generated lecture materials and teaching actions assessed and validated by expert educators. Experimental results show consistent gains in lecture content quality, embodied teaching quality, assessment, and personalization over existing approaches, positioning LectūraAgents as a pedagogically well-grounded framework for personalized learning at scale.","upvotes":31,"discussionId":"6a31fd86bc818ff14e453cf0","ai_summary":"LectūraAgents is a multi-agent framework that enables personalized learning through adaptive embodied teaching by mimicking professor-student interactions and generating coordinated teaching actions aligned with learner profiles.","ai_keywords":["multi-agent framework","personalized learning","embodied teaching","ProfessorAgent","teaching action-speech alignment","salience-based heuristics","temporal semantic segmentation","lecture content automation","simulations","multimodal instructional methods"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct"},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"61e52be53d6dbb1da842316a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61e52be53d6dbb1da842316a/gx0WGPcOCClXPymoKglc4.jpeg","isPro":false,"fullname":"Börje Karlsson","user":"tellarin","type":"user"},{"_id":"649959e57ac1bf03e2235111","avatarUrl":"/avatars/64ef99b3d6bc0c85934339bc6d00e122.svg","isPro":false,"fullname":"Yongqiang Chen","user":"lfhase","type":"user"},{"_id":"6438a9027de34e8ea7e4b257","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6438a9027de34e8ea7e4b257/vib8QSd1AWMr_bR9ig_xJ.jpeg","isPro":false,"fullname":"Jaward Sesay","user":"Jaward","type":"user"},{"_id":"64b964d31043081735692158","avatarUrl":"/avatars/209ae30594e39f9fbfa2972689b1a8b1.svg","isPro":false,"fullname":"Yu Bai","user":"woodenwhite","type":"user"},{"_id":"64bdd5cc76a6e2efccb22100","avatarUrl":"/avatars/5a0edc24283616dafc76ce5ec97ab5a0.svg","isPro":false,"fullname":"xuchaoyi","user":"co1one","type":"user"},{"_id":"69f42dfd7b0f7c52f4d8114f","avatarUrl":"/avatars/7bd294ac2826c05e557f25d7ff52f516.svg","isPro":false,"fullname":"Siqi Li","user":"LSQlilya","type":"user"},{"_id":"67bb2713b3920fd18e31ae80","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/gXlwum7WhyiH92b1XIrSL.png","isPro":false,"fullname":"HengWang","user":"WH1021","type":"user"},{"_id":"67cfc37d301174930f438c9d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/Mt1bVYOT8dn51UFs0eftg.png","isPro":false,"fullname":"songwenhao","user":"songwenhao123","type":"user"},{"_id":"65b36a28ed21070756e8a458","avatarUrl":"/avatars/1726d27aa0f37b162d54492b04fcdaa0.svg","isPro":false,"fullname":"Ziyi Bai","user":"ByZ0e","type":"user"},{"_id":"6708ccec79b2d9e035c4b524","avatarUrl":"/avatars/a0a46c58481321d0421e8238aab61b15.svg","isPro":false,"fullname":"li","user":"boyu1","type":"user"},{"_id":"66015275209f881caca4c821","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/aRH_6nZ5eTC5RZGGtMmgY.png","isPro":false,"fullname":"zhang","user":"WanyueZhang","type":"user"},{"_id":"643379416c6ecd58798421b3","avatarUrl":"/avatars/831db7eab2663abc33b176cf386b02f2.svg","isPro":false,"fullname":"Zhuoran Jin","user":"jinzhuoran","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.16428.md","query":{}}">

Papers

arxiv:2606.16428

LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

Published on Jun 15

· Submitted by

Börje Karlsson on Jun 17

Upvote

Authors:

Jaward Sesay ,

Börje F. Karlsson

Abstract

LectūraAgents is a multi-agent framework that enables personalized learning through adaptive embodied teaching by mimicking professor-student interactions and generating coordinated teaching actions aligned with learner profiles.

Generated by Qwen/Qwen2.5-Coder-32B-Instruct

Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. However, existing educational agents have primarily focused on lecture content automation and simulations, which often fall short of modelling multimodal and embodied instructional methods tailored for the individual learner. To this end, we propose LectūraAgents - a multi-agent framework that enables personalized learning through end-to-end adaptive embodied teaching. At its core, LectūraAgents mirrors a professor-student relationship, in which a ProfessorAgent leads a collaborative team of specialized subordinate agents through research, planning, review, and embodied delivery of lecture contents that adapt to a learner's needs. The framework offers three main contributions: (1) a hierarchical multi-agent architecture for end-to-end personalized learning; (2) an adaptive embodied teaching mechanism, wherein the ProfessorAgent executes visible and pedagogically motivated teaching actions (e.g., handwrite, highlight, underline, etc.) over contents in a teaching environment; and (3) a Teaching Action-Speech Alignment (TASA) algorithm that employs salience-based heuristics and temporal semantic segmentation to generate coherent teaching action sequences aligned with learner profiles. We evaluate LectūraAgents on diverse courses at high school, undergraduate, and graduate levels using sample-specific rubric-based analysis; with generated lecture materials and teaching actions assessed and validated by expert educators. Experimental results show consistent gains in lecture content quality, embodied teaching quality, assessment, and personalization over existing approaches, positioning LectūraAgents as a pedagogically well-grounded framework for personalized learning at scale.