Nemobot: Crafting Strategic Gaming LLM Agents for K-12 AI Education

Yuchen Wang; Shangxin Guo; Lin Ling; Chee Wei Tan

doi:10.1145/3657604.3664671

Nemobot: Crafting Strategic Gaming LLM Agents for K-12 AI Education

Yuchen Wang
, Shangxin Guo
, Lin Ling
, Chee Wei Tan

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

15 Citations (Scopus)

145 Downloads (CityUHK Scholars)

Abstract

Artificial intelligence (AI) permeates modern society and is poised for further integration across various domains. However, there exists a notable deficiency in equipping K-12 students with foundational AI understanding. This paper introduces a novel learning framework that leverages large language models (LLMs) and strategic gaming to teach K-12 students about the inner workings of AI. The framework consists of a chatbot programming and testing IDE that enables K-12 students to construct AI from scratch, engage in strategic gameplay to generate instant training data, and improve the AI heuristics with a data-driven learning mechanism. With a tiered curriculum catering to diverse proficiency levels and fostering synchronous collaboration, this framework efficiently adapts learning experiences to suit various groups of students, thereby facilitating learning at scale. Preliminary experiments validate the feasibility and vast potential of this approach, promising to revolutionize AI education in K-12 education.

© 2024 Copyright held by the owner/author(s).

Original language	English
Title of host publication	L@S '24
Subtitle of host publication	Proceedings of the Eleventh ACM Conference on Learning @ Scale
Publisher	Association for Computing Machinery
Pages	393-397
ISBN (Print)	979-8-4007-0633-2
DOIs	https://doi.org/10.1145/3657604.3664671
Publication status	Published - Jul 2024
Event	11th ACM Conference on Learning @ Scale, L@S 2024 - Atlanta, United States Duration: 18 Jul 2024 → 20 Jul 2024

Conference

Conference	11th ACM Conference on Learning @ Scale, L@S 2024
Place	United States
City	Atlanta
Period	18/07/24 → 20/07/24

Research Keywords

ai-assisted programming
chatbot programming
collaborative learning
gamification approach
generative ai
k-12 education
large language models(llms)

Publisher's Copyright Statement

This full text is made available under CC-BY-NC-SA 4.0. https://creativecommons.org/licenses/by-nc-sa/4.0/

Access Output

10.1145/3657604.3664671

237760603.pdfFinal Published version, 1.3 MBLicence: CC BY-NC-SA

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{8263c3fd6d48427582f473f004db5145,

title = "Nemobot: Crafting Strategic Gaming LLM Agents for K-12 AI Education",

abstract = "Artificial intelligence (AI) permeates modern society and is poised for further integration across various domains. However, there exists a notable deficiency in equipping K-12 students with foundational AI understanding. This paper introduces a novel learning framework that leverages large language models (LLMs) and strategic gaming to teach K-12 students about the inner workings of AI. The framework consists of a chatbot programming and testing IDE that enables K-12 students to construct AI from scratch, engage in strategic gameplay to generate instant training data, and improve the AI heuristics with a data-driven learning mechanism. With a tiered curriculum catering to diverse proficiency levels and fostering synchronous collaboration, this framework efficiently adapts learning experiences to suit various groups of students, thereby facilitating learning at scale. Preliminary experiments validate the feasibility and vast potential of this approach, promising to revolutionize AI education in K-12 education. {\textcopyright} 2024 Copyright held by the owner/author(s).",

keywords = "ai-assisted programming, chatbot programming, collaborative learning, gamification approach, generative ai, k-12 education, large language models(llms)",

author = "Yuchen Wang and Shangxin Guo and Lin Ling and Tan, \{Chee Wei\}",

year = "2024",

month = jul,

doi = "10.1145/3657604.3664671",

language = "English",

isbn = "979-8-4007-0633-2",

pages = "393--397",

booktitle = "L@S '24",

publisher = "Association for Computing Machinery",

address = "United States",

note = "11th ACM Conference on Learning @ Scale, L@S 2024 ; Conference date: 18-07-2024 Through 20-07-2024",

}

Nemobot: Crafting Strategic Gaming LLM Agents for K-12 AI Education. / Wang, Yuchen; Guo, Shangxin; Ling, Lin et al.
L@S '24: Proceedings of the Eleventh ACM Conference on Learning @ Scale. Association for Computing Machinery, 2024. p. 393-397.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Nemobot

T2 - 11th ACM Conference on Learning @ Scale, L@S 2024

AU - Wang, Yuchen

AU - Guo, Shangxin

AU - Ling, Lin

AU - Tan, Chee Wei

PY - 2024/7

Y1 - 2024/7

N2 - Artificial intelligence (AI) permeates modern society and is poised for further integration across various domains. However, there exists a notable deficiency in equipping K-12 students with foundational AI understanding. This paper introduces a novel learning framework that leverages large language models (LLMs) and strategic gaming to teach K-12 students about the inner workings of AI. The framework consists of a chatbot programming and testing IDE that enables K-12 students to construct AI from scratch, engage in strategic gameplay to generate instant training data, and improve the AI heuristics with a data-driven learning mechanism. With a tiered curriculum catering to diverse proficiency levels and fostering synchronous collaboration, this framework efficiently adapts learning experiences to suit various groups of students, thereby facilitating learning at scale. Preliminary experiments validate the feasibility and vast potential of this approach, promising to revolutionize AI education in K-12 education. © 2024 Copyright held by the owner/author(s).

AB - Artificial intelligence (AI) permeates modern society and is poised for further integration across various domains. However, there exists a notable deficiency in equipping K-12 students with foundational AI understanding. This paper introduces a novel learning framework that leverages large language models (LLMs) and strategic gaming to teach K-12 students about the inner workings of AI. The framework consists of a chatbot programming and testing IDE that enables K-12 students to construct AI from scratch, engage in strategic gameplay to generate instant training data, and improve the AI heuristics with a data-driven learning mechanism. With a tiered curriculum catering to diverse proficiency levels and fostering synchronous collaboration, this framework efficiently adapts learning experiences to suit various groups of students, thereby facilitating learning at scale. Preliminary experiments validate the feasibility and vast potential of this approach, promising to revolutionize AI education in K-12 education. © 2024 Copyright held by the owner/author(s).

KW - ai-assisted programming

KW - chatbot programming

KW - collaborative learning

KW - gamification approach

KW - generative ai

KW - k-12 education

KW - large language models(llms)

UR - https://www.scopus.com/pages/publications/85199905545

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85199905545&origin=recordpage

U2 - 10.1145/3657604.3664671

DO - 10.1145/3657604.3664671

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 979-8-4007-0633-2

SP - 393

EP - 397

BT - L@S '24

PB - Association for Computing Machinery

Y2 - 18 July 2024 through 20 July 2024

ER -

Nemobot: Crafting Strategic Gaming LLM Agents for K-12 AI Education

Abstract

Conference

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this