ORIGINAL RESEARCH article
Front. Educ.
Sec. STEM Education
"A Supplement, Not a Substitute" - Relational Experiences of Neurodiverse Graduate Students with an AI Virtual Mentor
Provisionally accepted
- University of Connecticut, Storrs, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Neurodiverse students in graduate STEM programs often lack access to affirming support. Large language models (LLMs) may offer a flexible supplement to traditional advising. However, little is known about how neurodiverse students perceive these tools or how prior experiences shape engagement. This study explores how neurodiverse graduate students perceived an LLM-powered Virtual Mentor tool, including how mindsets shaped engagement and how they perceived its usefulness and relational quality. Seventeen neurodiverse graduate students at a public R1 university used ChatGPT to engage with a Virtual Mentor tool configured with affirming language, safety guardrails, and a student profile. The Temporary Chat feature simulated a single-session interaction. Participants completed a pre survey, 20 minute interaction, interview, and follow up survey. A thematic analysis was conducted using chat and interview transcripts and survey responses. Participants’ preconceptions shaped engagement with the Virtual Mentor, influencing the tone of their interactions and their perceptions of its relational potential. Many described the tool as helpful and emotionally responsive while others found it mechanical or impersonal. Trust was higher for general advice and lower for technical questions. Some initially skeptical participants reported more favorable views after using the tool. While not a replacement for human relationships, many participants described the tool as a helpful, responsive, and emotionally supportive presence. Findings suggest that user mindsets shaped both the quality of the interactions and perceptions of the tool’s usefulness. The findings suggest opportunities for the implementation of student-centered AI tools as a part of responsive graduate support ecosystems.
Keywords: advising5, graduate STEM4, Large Language Models1, neurodiversity3, virtual mentoring2
Received: 16 Dec 2025; Accepted: 21 Jan 2026.
Copyright: © 2026 Syharat and Zaghi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Connie Mosher Syharat
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.