skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on April 11, 2026

Title: Developing LLM-Powered Trustworthy Agents for Personalized Learning Support
Large Language Models (LLMs) have shown promise in educational applications, but challenges such as hallucinations, lack of contextual relevance, and limited personalization impede their practical adoption. To address these issues, my research introduces MerryQuery, an LLM-powered educational agent that integrates Retrieval-Augmented Generation (RAG), rule-based content control, and Reinforcement Learning from Human Feedback (RLHF). The system features a dynamic learning profile module for adaptive personalization and a multi-step verification framework that cross-checks responses against external sources to enhance trustworthiness. A functional prototype of MerryQuery is being piloted in a real-world classroom. Preliminary results demonstrate improved response reliability and student understanding.  more » « less
Award ID(s):
1917885
PAR ID:
10644055
Author(s) / Creator(s):
Publisher / Repository:
The Association for the Advancement of Artificial Intelligence
Date Published:
Journal Name:
Proceedings of the AAAI Conference on Artificial Intelligence
Volume:
39
Issue:
28
ISSN:
2159-5399
Page Range / eLocation ID:
29301 to 29302
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. (, Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS '21))
    null (Ed.)
    To help facilitate play and learning, game-based educational activities often feature a computational agent as a co-player. Personalizing this agent's behavior to the student player is an active area of research, and prior work has demonstrated the benefits of personalized educational interaction across a variety of domains. A critical research challenge for personalized educational agents is real-time student modeling. Most student models are designed for and trained on only a single task, which limits the variety, flexibility, and efficiency of student player model learning. In this paper we present a research project applying transfer learning methods to student player models over different educational tasks, studying the effects of an algorithmic "multi-task personalization" approach on the accuracy and data efficiency of student model learning. We describe a unified robotic game system for studying multi-task personalization over two different educational games, each emphasizing early language and literacy skills such as rhyming and spelling. We present a flexible Gaussian Process-based approach for rapidly learning student models from interactive play in each game, and a method for transferring each game's learned student model to the other via a novel instance-weighting protocol based on task similarity. We present results from a simulation-based investigation of the impact of multi-task personalization, establishing the core viability and benefits of transferrable student models and outlining new questions for future in-person research. 
    more » « less
  2. (, Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems)
    To help facilitate play and learning, game-based educational activities often feature a computational agent as a co-player. Personalizing this agent's behavior to the student player is an active area of research, and prior work has demonstrated the benefits of personalized educational interaction across a variety of domains. A critical research challenge for personalized educational agents is real-time student modeling. Most student models are designed for and trained on only a single task, which limits the variety, flexibility, and efficiency of student player model learning. In this paper we present a research project applying transfer learning methods to student player models over different educational tasks, studying the effects of an algorithmic "multi-task personalization" approach on the accuracy and data efficiency of student model learning. We describe a unified robotic game system for studying multi-task personalization over two different educational games, each emphasizing early language and literacy skills such as rhyming and spelling. We present a flexible Gaussian Process-based approach for rapidly learning student models from interactive play in each game, and a method for transferring each game's learned student model to the other via a novel instance-weighting protocol based on task similarity. We present results from a simulation-based investigation of the impact of multi-task personalization, establishing the core viability and benefits of transferrable student models and outlining new questions for future in-person research. 
    more » « less
  3. ; ; ; ; ; (, ACM/IEEE International Conference on Human-Robot Interaction)
    Social telepresence robots (i.e., telerobots) are used for social and learning experiences by children. However, most (if not all) commercially available telerobot bodies were designed for adults in corporate or healthcare settings. Due to an adult-focused market, telerobot design has typically not considered important factors such as age and physical aspect in the design of robot bodies. To better understand how peer interactants can facilitate the identities of remote children through personalization of robot bodies, we conducted an exploratory study to evaluate collaborative robot personalization. In this study, child participants (N=28) attended an interactive lesson on robots in our society. After the lesson, participants interacted with two telerobots for personalization activities and a robot fashion show. Finally, participants completed an artwork activity on robot design. Initial findings from this study will inform our continued work on telepresence robots for virtual inclusion and improved educational experiences of remote children and their peers. 
    more » « less
  4. ; ; ; ; ; (, International Conference on Information Systems 2024)
    This paper examines the design and evaluation of Large Language Model (LLM) tutors for Python programming, focusing on personalization that accommodates diverse student backgrounds. It highlights the challenges faced by socioeconomically disadvantaged students in computing courses and proposes LLM tutors as a solution to provide inclusive educational support. The study explores two LLM tutors, Khanmigo and CS50.ai, assessing their ability to offer personalized learning experiences. By employing a focus group methodology at a public minority-serving institution, the research evaluates how these tutors meet varied educational goals and adapt to students’ diverse needs. The findings underscore the importance of advanced techniques to tailor interactions and integrate programming tools based on students' progress. This research contributes to the understanding of educational technologies in computing education and provides insights into the design and implementation of LLM tutors that effectively support equitable student success. 
    more » « less
  5. ; ; ; (, 2019 14th International Conference on Computer Science & Education (ICCSE))
    It is believed that if students are well engaged in the learning process within the classroom, they will continue the learning process independently outside the classroom. To facilitate such out-of-class learning, there is a plethora of traditional techniques with a variety of learning theoretical backgrounds. While out-of-class activities based on these techniques have shown to improve a student’s overall quality of learning, traditional activities lack the supervision, instant feedback, and personalization that the current generation of students expects. With the rising cost of college tuition, many of today’s students are working more hours outside of an educational setting and therefore need more supervision and encouragement than their predecessors. These factors make traditional out-of-class activities not effective to achieve the desired level of student learning and engagement outside the classroom. The faculty needs to rethink ways to redesign traditional out-of-class activities to make these activities more effective for this generation of students. This paper presents a review of the literature on and categorization of traditional out-of-class activities. The paper also discusses the results of a survey of what the faculty is doing to engage and continue student learning outside the classroom. Finally, the paper presents a new way of designing and delivering out-of-class activities that have the potential to increase student engagement with the help of instructional scaffolding, interactive activities, and personalization and adaptation. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email