Skip to content

Desiderata for AI Tutors as Knowledge-Building Partners

· 0 citations · 81 references

TL;DR

This work examines six key dimensions: cognitive engagement, cultural responsiveness, formative assessment, formative assessment, power dynamics, accountability, and metacognition, outlining desiderata for LLM tutors in each area and reimagining LLMs’ role.

View source

Similar papers

Conference Open access Aug 2026

Methodologies for Improving the Quality of AI Tutoring in K-12 Education

Many AI tutors leverage large language models (LLMs) today. Given that LLMs are opaque black boxes, robust evaluation and live experimentation to measure the impact of every change are essential. We pioneered AI-powered tutoring for K-12 with the launch of Khanmigo (Khan Academy, 2023). We describe the metrics we use t...

Tushar Udeshi, Anna Khazenzon, Kabir Khan et al. · 0 citations
Conference Open access Sep 2026

LLM-Based Intelligent Tutoring Systems: A Survey

Large Language Models (LLMs) are reshaping the design and capabilities of intelligent tutoring systems (ITS) by providing powerful generative, reasoning and interaction abilities, which surpass traditional rule-based approaches. This survey presents a structured overview of LLM-based ITS and analyzes how these models t...

Li Kong, Jian-Wen Sun, Junsheng Zhou et al. · 0 citations
Preprint Aug 2026

LLM Pedagogical Behavior in AI Tutoring Interactions

A five-level scale is developed, validated against human annotations, that characterizes responses according to the degree of direct assistance LLMs provide when students use them as tutors in authentic learning interactions and provides an empirical baseline for LLM assistance in tutoring interactions and a measuremen...

Suhyeon Lee, Juneha Baek, Jaehyeong Park et al. · 0 citations
Book Open access Aug 2026

Towards Human-Centered Large Language Models for Personalized Programming Education

Large Language Models (LLMs) are increasingly used in computing education to support programming practice and generate explanations [5, 9]. However, current LLM-based systems are not pedagogically aligned and fail to adapt to learners’ prior knowledge, often producing feedback that is too advanced or oversimplified [8]...

Jing Fan · 0 citations
Open access Sep 2026

Instructional Control for AI-Assisted Learning: Custom AI Tools for Genre-Based Writing

The release of ChatGPT in 2022 introduced both transformative opportunities and notable challenges for writing instruction and heightened instructors’ concerns about its impact on teaching and student learning. To explore how GenAI may enhance business communication in the age of AI while mitigating its negative effe...

Jun-Hua Wang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.