Building Agents that Help Students Learn

The paper addresses the challenge of leveraging generative AI (gen AI) for equitable, high-quality education. The authors identify difficulties in translating pedagogical principles into effective AI prompts and the lack of robust evaluation practices as key obstacles. They introduce LearnLM-Tutor, a fine-tuned model based on Gemini, guided by seven educational benchmarks developed with educators and

The paper introduces an AI-driven solution using open-source LLaMA-2 models to improve scalability in answering student questions on online platforms. By integrating retrieval-augmented generation, fine-tuning, and preference optimization, the approach achieves a 30% improvement in answer quality on a Piazza dataset. This work lays the foundation for customizable AI teaching assistants.