Athena: A GenAI-Powered Programming Tutor Based on Open-Source LLM

With the rapid growth of generative artificial intelligence (GenAI), it is important to find ways to utilize them for academic advantage. GenAI tools embody immense potential in providing personalized feedback to students any time anywhere, and hence can provide a reliable helping hand to teachers who often experience burnout in large classes and are burdened with administrative tasks. While current GenAI tools like ChatGPT are helpful, they occasionally offer misinformation - a phenomenon known as hallucination, undermine critical thinking by providing direct answers to questions, and, as paid services, can further widen the digital divide. Against the backdrop of these problems, this research introduces Athena, a GenAI programming mentor based on an open-source large language model (LLM), constructed to guide programming learners to think critically and provide reliable information leveraging retrieval augmented generation. Its impact on learning outcomes was measured by feedback from programming students. Most students have given a positive response, saying that their motivation to keep learning and their confidence in their abilities have increased. These results imply that having a reliable AI mentor that can guide students at all times can have a positive impact in self-directed learning process.

Authors

Institutions

Publication Details

Published
2025-03-29
DOI
https://doi.org/10.1109/icct-pacific63901.2025.11012850
Citations
2
Primary Topic
Intelligent Tutoring Systems and Adaptive Learning
Type
article
Field-Weighted Citation Impact
4.96
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Athena: A GenAI-Powered Programming Tutor Based on Open-Source LLM

M. Fahim Ferdous Khan, Ya‐Hui Lin, Ken Sakamura
2 citations
Intelligent Tutoring Systems and Adaptive Learning
4.96
article

Athena: A GenAI-Powered Programming Tutor Based on Open-Source LLM

M. Fahim Ferdous Khan, Ya‐Hui Lin, Ken Sakamura
article en
2 citations

Abstract

With the rapid growth of generative artificial intelligence (GenAI), it is important to find ways to utilize them for academic advantage. GenAI tools embody immense potential in providing personalized feedback to students any time anywhere, and hence can provide a reliable helping hand to teachers who often experience burnout in large classes and are burdened with administrative tasks. While current GenAI tools like ChatGPT are helpful, they occasionally offer misinformation - a phenomenon known as hallucination, undermine critical thinking by providing direct answers to questions, and, as paid services, can further widen the digital divide. Against the backdrop of these problems, this research introduces Athena, a GenAI programming mentor based on an open-source large language model (LLM), constructed to guide programming learners to think critically and provide reliable information leveraging retrieval augmented generation. Its impact on learning outcomes was measured by feedback from programming students. Most students have given a positive response, saying that their motivation to keep learning and their confidence in their abilities have increased. These results imply that having a reliable AI mentor that can guide students at all times can have a positive impact in self-directed learning process.

Toyo University (JP)
Quality Education
Openalex Percentile: Top 5%
Intelligent Tutoring Systems and Adaptive Learning
4.96
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.