AICoFe: Implementation and Deployment of an AI-Based Collaborative Feedback System for Higher Education

TL;DR

This paper introduces AICoFe, an AI-driven system that enhances peer feedback quality in higher education through a multi-LLM pipeline and human-in-the-loop workflows.

Contribution

It presents a modular AI system with a hybrid data infrastructure and a teacher-in-the-loop process for improved feedback in educational settings.

Findings

System effectively synthesizes feedback from multiple LLMs.

Teacher-in-the-loop workflow improves feedback relevance and quality.

Hybrid SQL and MongoDB infrastructure ensures traceability.

Abstract

Effective peer feedback is essential for developing critical reflection in higher education, yet its impact is often limited by the inconsistent quality of student-generated comments. This paper presents the implementation and deployment of AICoFe (AI-based Collaborative Feedback), a system designed to bridge this gap through a human-centered AI approach. We describe a modular architecture that orchestrates a multi-LLM pipeline, utilizing GPT-4.1-mini, Gemini 2.5 Flash, and Llama 3.1, to synthesize quantitative rubric data and qualitative observations into coherent, actionable feedback. Key to the system is a "teacher-in-the-loop" mediation workflow, where educators use specialized Learning Analytics dashboards to curate and refine AI-generated drafts before delivery. Furthermore, we detail the underlying data infrastructure, which employs a hybrid SQL and MongoDB strategy to ensure traceability and manage semi-structured feedback versions.