From First Draft to Final Insight: A Multi-Agent Approach for Feedback Generation

TL;DR

This study introduces a multi-agent G-E-RG approach utilizing LLMs to significantly improve the quality, accuracy, and effectiveness of automated feedback generation in educational settings.

Contribution

It proposes a novel multi-agent framework with generation, evaluation, and regeneration phases, enhancing feedback quality beyond existing LLM-based methods.

Findings

Evaluation accuracy increased by up to 13% (p<0.001)

Effective feedback components rose from 27.72% to 98.49%

Feedback simplicity was significantly improved (p<0.001)

Abstract

Producing large volumes of high-quality, timely feedback poses significant challenges to instructors. To address this issue, automation technologies-particularly Large Language Models (LLMs)-show great potential. However, current LLM-based research still shows room for improvement in terms of feedback quality. Our study proposed a multi-agent approach performing "generation, evaluation, and regeneration" (G-E-RG) to further enhance feedback quality. In the first-generation phase, six methods were adopted, combining three feedback theoretical frameworks and two prompt methods: zero-shot and retrieval-augmented generation with chain-of-thought (RAG_CoT). The results indicated that, compared to first-round feedback, G-E-RG significantly improved final feedback across six methods for most dimensions. Specifically:(1) Evaluation accuracy for six methods increased by 3.36% to 12.98% (p<0.001); (2) The proportion of feedback containing four effective components rose from an average of 27.72% to an average of 98.49% among six methods, sub-dimensions of providing critiques, highlighting strengths, encouraging agency, and cultivating dialogue also showed great enhancement (p<0.001); (3) There was a significant improvement in most of the feature values (p<0.001), although some sub-dimensions (e.g., strengthening the teacher-student relationship) still require further enhancement; (4) The simplicity of feedback was effectively enhanced (p<0.001) for three methods.