Using Generative AI and Multi-Agents to Provide Automatic Feedback
It addresses a key gap for educators and researchers by offering a more reliable solution for scalable and personalized feedback in formative assessments, though it is incremental as it builds on existing multi-agent and GenAI approaches.
This study tackled the problem of improving automatic feedback in education by developing a multi-agent system called AutoFeedback to reduce errors like over-praise and over-inference in generative AI, testing it on 240 student responses and showing significant reductions in these errors.
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 developed a multi-agent system consisting of two AI agents: one for generating feedback and another for validating and refining it. The system was tested on a dataset of 240 student responses, and its performance was compared to that of a single-agent LLM. Results showed that AutoFeedback significantly reduced the occurrence of over-praise and over-inference errors, providing more accurate and pedagogically sound feedback. The findings suggest that multi-agent systems can offer a more reliable solution for generating automated feedback in educational settings, highlighting their potential for scalable and personalized learning support. These results have important implications for educators and researchers seeking to leverage AI in formative assessments, offering a pathway to more effective feedback mechanisms that enhance student learning outcomes.