Arav Agarwal

According to our database, Arav Agarwal authored at least 14 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

A comparative study of AI-generated and human-crafted learning objectives in computing education.

Aidan Doyle, Pragnya Sridhar, Arav Agarwal, Jaromír Savelka, Majd Sakr

J. Comput. Assist. Learn., 2025

AI Technicians: Developing Rapid Occupational Training Methods for a Competitive AI Workforce.

Jaromír Savelka, Can Kültür, Arav Agarwal, Christopher Bogart, Heather Burte, Adam Zhang, Majd Sakr

Proceedings of the 56th ACM Technical Symposium on Computer Science Education V. 1, 2025

Generating Effective Distractors for Introductory Programming Challenges: LLMs vs Humans.

Mohammad Hassany, Peter Brusilovsky, Jaromír Savelka, Arun Balajiee Lekshmi Narayanan, Kamil Akhuseyinoglu, Arav Agarwal, Rully Agus Hendrawan

Proceedings of the 15th International Learning Analytics and Knowledge Conference, 2025

Generating Distractors for Code Completion Problems: Can LLM Assist Instructors?

Mohammad Hassany, Kamil Akhuseyinoglu, Arun Balajiee Lekshmi Narayanan, Arav Agarwal, Jaromír Savelka, Peter Brusilovsky

Proceedings of the 38th International Florida Artificial Intelligence Research Society Conference, 2025

2024

A Benchmark for Testing the Capabilities of LLMs in Assessing the Quality of Multiple-choice Questions in Introductory Programming Education.

Aninditha Ramesh, Arav Agarwal, Jacob Arthur Doughty, Ketan Ramaneti, Jaromír Savelka, Majd Sakr

Proceedings of the 2024 ACM Virtual Global Computing Education Conference V. 1, 2024

Understanding the Role of Temperature in Diverse Question Generation by GPT-4.

Arav Agarwal, Karthik Mittal, Aidan Doyle, Pragnya Sridhar, Zipiao Wan, Jacob Arthur Doughty, Jaromír Savelka, Majd Sakr

Proceedings of the 55th ACM Technical Symposium on Computer Science Education, 2024

A Comparative Study of AI-Generated (GPT-4) and Human-crafted MCQs in Programming Education.

Jacob Doughty, Zipiao Wan, Anishka Bompelli, Jubahed Qayum, Taozhi Wang, Juran Zhang, Yujia Zheng, Aidan Doyle, Pragnya Sridhar, Arav Agarwal, Christopher Bogart, Eric Keylor, Can Kültür, Jaromír Savelka, Majd Sakr

Proceedings of the 26th Australasian Computing Education Conference, 2024

2023

MultiZoo and MultiBench: A Standardized Toolkit for Multimodal Deep Learning.

Paul Pu Liang, Yiwei Lyu, Xiang Fan, Arav Agarwal, Yun Cheng, Louis-Philippe Morency, Ruslan Salakhutdinov

J. Mach. Learn. Res., 2023

From GPT-3 to GPT-4: On the Evolving Efficacy of LLMs to Answer Multiple-choice Questions for Programming Classes in Higher Education.

Jaromír Savelka, Arav Agarwal, Christopher Bogart, Majd Sakr

CoRR, 2023

MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning.

Paul Pu Liang, Yiwei Lyu, Xiang Fan, Arav Agarwal, Yun Cheng, Louis-Philippe Morency, Ruslan Salakhutdinov

CoRR, 2023

Can Generative Pre-trained Transformers (GPT) Pass Assessments in Higher Education Programming Courses?

Jaromír Savelka, Arav Agarwal, Christopher Bogart, Yifan Song, Majd Sakr

Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education V. 1, 2023

Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses.

Jaromír Savelka, Arav Agarwal, Marshall An, Chris Bogart, Majd Sakr

Proceedings of the 2023 ACM Conference on International Computing Education Research, 2023

Large Language Models (GPT) Struggle to Answer Multiple-Choice Questions About Code.

Jaromír Savelka, Arav Agarwal, Christopher Bogart, Majd Sakr

Proceedings of the 15th International Conference on Computer Supported Education, 2023

Harnessing LLMs in Curricular Design: Using GPT-4 to Support Authoring of Learning Objectives.

Pragnya Sridhar, Aidan Doyle, Arav Agarwal, Christopher Bogart, Jaromír Savelka, Majd Sakr

Proceedings of the Workshop on Empowering Education with LLMs, 2023