CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring

Jiamin Su, Yibo Yan, Zhuoran Gao, Han ZHANG, Xiang Liu, Huiyu Zhou, Xuming Hu

Keywords: Automated Essay Scoring, Multi-Agent System, Multimodal Large Language Models

TL;DR: CAFES is the first collaborative multi-agent framework specifically designed for AES, supporting multimodal inputs and multi-granular scoring.

Abstract: Automated Essay Scoring (AES) is crucial for modern education, particularly with the increasing prevalence of multimodal assessments. However, traditional AES methods struggle with evaluation generalizability and multimodal perception, while even recent Multimodal Large Language Model (MLLM)-based approaches can produce hallucinated justifications and scores misaligned with human judgment. To address the limitations, we introduce CAFES, the first collaborative multi-agent framework specifically designed for AES. It orchestrates three specialized agents: an Initial Scorer for rapid, trait-specific evaluations; a Feedback Pool Manager to aggregate detailed and evidence-grounded feedback; and a Reflective Scorer that iteratively refines scores based on this feedback to enhance human alignment. Extensive experiments, using widely adopted MLLMs, achieve an average relative improvement of 21% in Quadratic Weighted Kappa (QWK) against ground truth, with particularly strong gains in grammatical and lexical diversity. Our proposed CAFES paves the way for an intelligent multimodal AES system. The code and dataset are available at https://anonymous.4open.science/r/CAFES-C87F/.

Submission Number: 18