Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback Agents
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (46) · 39594-39602
DOI: 10.1609/aaai.v40i46.41311 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chenyu Zhang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
Formative feedback is widely recognized as one of the most effective drivers of student learning, yet it remains difficult to implement equitably at scale. In large or low-resource courses, instructors often lack the time, staffing, and bandwidth required to review and respond to every student reflection, creating gaps in support precisely where learners would benefit most. This paper presents a theory-grounded system that uses five coordinated role-based LLM agents (Evaluator, Equity Monitor, Metacognitive Coach, Aggregator, and Reflexion Reviewer) to score learner reflections with a shared rubric and to generate short, bias-aware, learner-facing comments. The agents first produce structured rubric scores, then check for potentially biased or exclusionary language, add metacognitive prompts that invite students to think about their own thinking, and finally compose a concise feedback message of at most 120 words. The system includes simple fairness checks that compare scoring error across lower and higher scoring learners, enabling instructors to monitor and bound disparities in accuracy. We evaluate the pipeline in a 12-session AI literacy program with adult learners. In this setting, the system produces rubric scores that approach expert-level agreement, and trained graders rate the AI-generated comments as helpful, empathetic, and well aligned with instructional goals. Taken together, these results show that multi-agent LLM systems can deliver equitable, high-quality formative feedback at a scale and speed that would be impossible for human graders alone. The approach demonstrates how structured agent roles, fairness checks, and learning-science principles can work together to support instructors while preserving pedagogical intent. More broadly, the work points toward a future where feedback-rich learning becomes feasible for any course size or context, advancing long-standing goals of equity, access, and instructional capacity in education.
Zitieren
APA
Zhang, C., & Luo, X. (2026). Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback Agents. Proceedings of the AAAI Conference on Artificial Intelligence, 40(46), 39594-39602. https://doi.org/10.1609/aaai.v40i46.41311
Vancouver
Zhang C, Luo X. Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback Agents. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(46):39594-39602. doi:10.1609/aaai.v40i46.41311
BibTeX
@article{Zhang2026,
author = {Zhang, Chenyu and Luo, Xiaohang},
title = {Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback Agents},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {46},
pages = {39594--39602},
doi = {10.1609/aaai.v40i46.41311}
}
EUVIMED