Skip to content
Review Open access

Development and Implementation of an AI Tutor To Scaffold Problem-Solving in Introductory Chemistry

Sep 2026 · Journal of Chemical Education · Vol 103, pp. 5555 - 5563 · 0 citations · 39 references
Medicine

TL;DR

The design, implementation, and evaluation of STEPS (STEM Tutor for Effective Problem Solving), an AI tutor particularly designed to guide students in creating a problem-solving plan without divulging solutions, are presented.

Abstract

Developing problem-solving competency is a central goal of undergraduate chemistry education, yet many students struggle to engage productively with complex, multistep problems. At the same time, the rapid adoption of large language model (LLM)–based tools by students in STEM courses raises concerns about over-reliance and uncritical use, potentially undermining learning. In this work, we present the design, implementation, and evaluation of STEPS (STEM Tutor for Effective Problem Solving), an AI tutor particularly designed to guide students in creating a problem-solving plan without divulging solutions. The tutor was deployed in an introductory chemistry course at an R1 university, and its impact was examined using performance data, Likert-scale survey responses, and qualitative analysis of student reflections. Students demonstrated high performance on STEPS-assisted problems and reported strong confidence in their solutions. Survey results indicated consistently high perceptions of helpfulness. Qualitative analysis revealed that students valued the tutor’s guidance in organizing their thinking and checking reasoning without giving away solutions. These findings suggest that carefully designed, task-specific AI tutors can promote productive engagement with problem solving while mitigating risks associated with uncritical AI use in chemistry education.

Read PDF

Similar papers

Preprint Oct 2026

AI-Guided Assignments in Practice: Students'Experiences in a Large Introductory Statistics Course

Results on 134 students show meaningful gains in self-reported confidence, with over 80% agreeing that the assignments improved their comprehension of course material and their ability to interpret statistical results; gains were largest among students who started with lower confidence, suggesting this approach may hel...

E. Furfaro, Katherine Elizabeth Lovelace, Yu-Hang Zhang et al. · 0 citations
Review Open access Oct 2026

Adoption and Impacts of a Socratic Generative AI Tutor in Undergraduate Algebra

Most students reported using Khanmigo for homework help and exam prep, though lack of visuals and the Socratic design limited perceived usefulness for some students, and instrumental help seeking was positively correlated with use.

Caitlin K. Kirby, Kanyi Eing, J. Zimmerman et al. · 0 citations
Open access Sep 2026

Development of an Electronic Student Worksheet Based on Mathematical Modeling for Junior High School Mathematics

Mathematics instruction in junior high school still struggles to connect abstract concepts with real-life problem-solving, particularly in the social arithmetic topic, where textbook-based teaching limits students' conceptual understanding. This study aimed to develop an electronic student worksheet (E-LKPD) grounded i...

Rinda Ulpaliana, Yamanto Isa, Heni Rita Susila · 0 citations
Review Open access Oct 2026

Exploring student and teacher perspectives on critical thinking with generative AI: early insights from the EduPartnerAI platform

The integration of artificial intelligence (AI) into education has raised important questions about its implications for students’ analytical reasoning and independent judgment. ChatGPT, a generative AI model capable of producing human-like responses, is widely used in academic contexts, yet its educational value req...

Stefania-Carmen Dobre, Elvira Popescu · 0 citations
Review Open access Oct 2026

AI-supported pedagogical pipeline for computing students’ research competence

This study evaluates an artificial intelligence (AI)-enabled co-curricular student club model implemented at two regional universities, organized as a staged four-part pipeline comprising competitive programming, hackathon prototyping, startup/project development, and final project defense. A matched pre/post design wa...

Кazimova Dinara, Aliyeva Dinara, Kultan Jaroslav et al. · 0 citations
Review Open access Sep 2026

Problem-Based Learning Assisted by Student Worksheets to Improve Mathematical Problem-Solving Skills of Primary School Students

Mathematical problem-solving is a foundational competency in elementary education, yet many fourth-grade students continue relying on procedural, drill-oriented strategies rather than systematic reasoning when facing non-routine problems. This study aimed to describe the implementation of a Problem-Based Learning (PBL)...

Nurlina Maharani, W. Wuryandani, Anwar Novianto · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.