Multi-agent large language models promise flexible, modular architectures for delivering personalized educational content. Drawing on a pilot randomized controlled trial with middle school students (n = 23), we introduce a two-agent GPT-4 framework in which a Profiler agent infers learner-specific preferences and a Rewrite agent dynamically adapts science passages via an explicit message-passing protocol. We implement structured system and user prompts as inter-agent communication schemas to enable real-time content adaptation. The results of an ordinal logistic regression analysis hinted that students may be more likely to prefer texts aligned with their profile, demonstrating the feasibility of multi-agent system-driven personalization and highlighting the need for additional work to build upon this pilot study. Beyond empirical validation, we present a modular multi-agent architecture detailing agent roles, communication interfaces, and scalability considerations. We discuss design best practices, ethical safeguards, and pathways for extending this framework to collaborative agent networks—such as feedback-analysis agents—in K-12 settings. These results advance both our theoretical and applied understanding of multi-agent LLM systems for personalized learning.

Large language models (LLMs), including OpenAI's GPT-series, have made significant advancements in recent years. Known for their expertise across diverse subject areas and quick adaptability to user-provided prompts, LLMs hold unique potential as Personalized Learning (PL) tools. Despite this potential, their application in K-12 education remains largely unexplored. This paper presents one of the first randomized controlled trials (n = 23) to evaluate the effectiveness of GPT-4 in personalizing educational science texts for middle school students. In this study, GPT-4 was used to profile student learning preferences based on choices made during a training session. For the experimental group, GPT-4 was used to rewrite science texts to align with the student's predicted profile while, for students in the control group, texts were rewritten to contradict their learning preferences. The results of a Mann-Whitney U test showed that students significantly preferred (at the .10 level) the rewritten texts when they were aligned with their profile (p = .059). These findings suggest that GPT-4 can effectively interpret and tailor educational content to diverse learner preferences, marking a significant advancement in PL technology. The limitations of this study and ethical considerations for using artificial intelligence in education are also discussed.

The aging of steel bridge girders is often compounded by corrosion at girder ends due to leaking deck joints. With 6.8% of U.S. bridges in poor condition, there is an urgent need for accurate yet efficient methods to assess the residual load-bearing capacity of corroded girders. Traditional assessment methods often represent corrosion as uniform section loss or rely on simplified surface representations, compromising the accuracy of the residual capacity estimation. To address these limitations, this paper proposes a novel approach for characterizing the geometry of locally corroded steel surfaces by decomposing the corroded region into high-frequency (fine surface textures) and low-frequency (global shape) components using multilevel Lanczos filters. Validated using 3D scans collected from a 57-year-old in-service bridge, our case study shows that each high-frequency component can be modeled as a stationary random field using a Hole-Gaussian autocorrelation function, with correlation lengths inversely proportional to the cutoff frequencies of the Lanczos filters. The low-frequency component is accurately characterized by a bivariate Lagrange polynomial fitted via a 4 × 4 coefficient matrix, with average volume errors of less than 1% and normalized root mean square errors under 10% for most surfaces. The technique results in a manage set of parameters that can be used to investigate the effects of corrosion damage on the behavior of corroded steel members.