Using Generative AI and Multi-Agents to Provide Automatic Feedback

This study develops and evaluates a multi-agent AI system (AutoFeedback) to generate and validate automatic feedback for student constructed responses in science assessments, comparing its performance against single-agent LLMs in reducing over-praise and over-inference errors. The research tests the system on 240 student responses to science assessment items and demonstrates improved feedback quality through the multi-agent approach.

This study investigates the use of generative AI and multi-agent systems to provide automatic feedback in educational contexts, particularly for student constructed responses in science assessments. The research addresses a key gap in the field by exploring how multi-agent systems, called AutoFeedback, can improve the quality of GenAI-generated feedback, overcoming known issues such as over-praise and over-inference that are common in single-agent large language models (LLMs). The study develope

Study Type

Source

Framework Categories

Tool Types

Tags