Leveraging large language models (LLMs) to enhance student inquiry in a nanochemistry teaching laboratory: a Fenton-like oxidation using recyclable ferrite nanoparticle (NP) catalysts.

Abstract

3d transition metal ferrite NPs are unique nanostructured materials owing to their tunable magnetic, electrical, and structural properties, which arise from the interplay of different transition metal ions in the spinel lattice structure. Their relatively simple co-precipitation-based synthesis provides a foundation for students to explore diverse functional properties, including energy band-gap, surface charge, capping ligand dynamics, size, morphology, and crystal phase. The high surface area and tunable electronic structures of MFe 2 O 4 (M = Mn, Co, Ni) enhance catalytic efficiency for hydrogen peroxide activation in a Fenton-like oxidative catalysis process, offering a compelling model for sustainable environmental remediation through pollutant degradation. This laboratory module integrates Large Language Model (LLM) agents as active pedagogical partners to bridge the gap between benchtop experimentation and authentic research. Students utilize LLMs to propose experimental parameters, analyze complex datasets, and simulate environmental impact. By interacting with LLMs throughout the synthesis of Tween-20 capped ferrite NPs, their characterization, and catalytic application including catalysis recycling, undergraduates gain handson experience in nanomaterial chemistry while mastering the digital literacy skills required in modern laboratories. This approach transforms a standard 'mini-project' into a dynamic, inquiry-based experience that aligns with United Nations Sustainable Development Goals (SDG) 4 (Quality Education for All), 6 (Clean Water and Sanitation), and 10 (Reduced Inequalities), effectively preparing students for the rigours of independent scientific inquiry in an evolving educational and research landscape where the conscientious use of LLMs help students take ownership of their own learning.