2026 ASEE Annual Conference & Exposition

Exploring Student Perceptions of Working with Generative AI in Agent-Based Modeling

Presented at Generative AI in BME Courses

Generative artificial intelligence (AI) tools such as ChatGPT and Claude are changing the way students engage in coursework in the biomedical engineering classroom. The rapid evolution of AI tools has outpaced the collective understanding of how these tools influence students’ comprehension of course material and learning of distinct technical skills. In this study, we investigate students’ use of AI in a course that teaches a type of computational modeling called agent-based modeling. In an agent-based model (ABM), the rules governing the behavior of biological agents in the model are derived from scientific literature and encoded into executable code. The ABM building process provides a unique test-case for the use of AI because it requires a baseline understanding of a biological system through literature and the technical skills for the coding implementation.
In this study, we employed a parallel mixed methods approach with two surveys and one written reflection. The research was conducted in a combined undergraduate and graduate level biomedical engineering course that teaches computational approaches for systems biology at a large R1institution in the mid-Atlantic United States. The participants from this course include 7 Ph.D. students and 27 undergraduate students. Students were placed into groups and tasked with developing an ABM of a biological system of their choosing. Before creating their model, students independently completed a Likert scale survey assessing prior use of AI and perceived usefulness. After developing their models, each student submitted their model rules to an AI tool and asked the AI tool to generate the corresponding code. Students separately submitted their unmodified code and asked the AI tool to revise it. Students also completed a written reflection and an additional Likert scale survey about their experiences with AI. Written reflections were qualitatively coded until reaching 80% agreement between two researchers.
Students reported some advantage to using AI to develop their ABM. AI tools helped students understand the system they were modeling, and the fundamental principles of constructing an ABM. Students who frequently used AI for other classes and assignments reported greater proficiency with AI tools, but this was also accompanied by increased feelings of dependence on AI. Many students also noted a clear disconnect between the model AI said it had encoded, and the actual code. The code produced by AI was also erroneous, and students frequently noted having to correct syntax.
Overall, these data suggest that while AI can support students in learning and building computational models of biological systems, there could be an advantage to teaching targeted use of AI as a tool for specific contexts to students in the classroom. Future work will examine the use of AI in other types of computational modeling across both graduate and undergraduate levels of instruction.

Authors

Dorothy N. Beck University of Virginia [biography]

Dorothy Beck is a junior at the University of Virginia studying Biomedical Engineering. She is interested in understanding how, why, and when students use artificial intelligence in their coursework.
Ms. Anne Marguerite McAlister http://orcid.org/0000-0002-4155-251X University of Virginia [biography]

Dr. Anne M. McAlister is an Assistant Professor in the First Year Engineering Center at the University of Virginia. She has her PhD in Education and MS in Systems Engineering from the University of Virginia, and her BS in Chemical Engineering from The Ohio State University. Her research focuses primarily on identity and qualitative research methods.
Anna Leyf Peirce Starling http://orcid.org/0009-0000-8944-0675 University of Virginia [biography]

Anna Leyf Peirce Starling (Leyf Starling) is a founding faculty member and current Director of the First Year Engineering Center at the University of Virginia. She is currently developing curriculum and teaching the Foundations of Engineering 1 and 2 courses as well as advising 1st year engineering students.
Starling earned a BS in Mechanical Engineering (UVA ‘03); enhanced that with a MAT in Special Education-General Curriculum (University of North Carolina- Charlotte ‘07); and she has taught math, science, engineering, and robotics for over 20 years in both public and private middle schools, high schools, and universities. Her goal and passion is to make engineering accessible at all levels and across disciplines.
Starling has led professional development trainings on integrating engineering in the K-12 classroom, spent over 10 years consulting for the NSF funded Research Experience for Teachers program at Michigan State University, was editor and contributor to NSF-funded TeachEngineering.org, has presented at ASEE and NIH conferences on promising practices for making engineering accessible, has collaborated closely with the DO-IT Center at the University of Washington, was the founder and director of the Summer Engineering Experience for Students with Visual Impairments and Blindness, and co-founded and co-coached FIRST Robotics Competition Team DARC SIDE.
Currently, her focus is on developing and implementing ways to best support 1st year students and transfer students coming into the field of engineering. She is working to advance the field of engineering education through accessibility while also researching, developing, and integrating practices to support students' growth in teamwork, leadership, communication, and meaningful engagement in the community. Through this effort, she also works to advance ways to integrate emerging technologies as productive tools to support student learning and assessment.
Dr. Timothy E. Allen http://orcid.org/0000-0001-5768-6339 University of Virginia [biography]

Dr. Timothy E. Allen is a Professor in the Department of Biomedical Engineering at the University of Virginia. He received a B.S.E. in Biomedical Engineering at Duke University and M.S. and Ph.D. degrees in Bioengineering at the University of California, San Diego. Dr. Allen's teaching activities include coordinating the undergraduate teaching labs and the Capstone Design sequence in the BME department at the University of Virginia, and his research interests are in the fields of computational biology and bioinformatics. He is also interested in evaluating the pedagogical approaches optimal for teaching lab concepts and skills, computational modeling approaches, and professionalism within design classes. He is active within the Biomedical Engineering Division of the American Society for Engineering Education and previously served on the executive committee of this division (Program Chair 2011, Division Chair 2012, and Nominating Committee Chair 2013). Dr. Allen is an elected fellow of the American Institute for Medical and Biological Engineering (AIMBE), and he is the recipient of over a dozen teaching awards, including the All-University Teaching Award at UVA. He is also PI on a recently renewed NSF REU site (now in its tenth year) focused on multi-scale systems bioengineering and biomedical data sciences, a collaboration involving faculty in SEAS, SOM, SDS, and CLAS at UVA, as well as five partner institutions in the mid-Atlantic and Southeast.
Elsje Pienaar Purdue University at West Lafayette (COE)
Dr. Shayn Peirce-Cottler University of Virginia [biography]

I am Professor of Biomedical Engineering at the University of Virginia. I have joint appointments in the Department of Plastic Surgery and the Department of Ophthalmology.

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 21, 2026, and to all visitors after the conference ends on June 24, 2026

« View session