# Towards an Efficient, Customizable, and Accessible AI Tutor

arXiv: https://arxiv.org/abs/2510.06255 · HTML: https://mlsanity.com/paper/2510.06255/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 8 of its 13 references that are in the map.
- First posted on arXiv 4 Oct 2025.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)

## Builds on (most cited first, 8 of 8)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [Benchmarking Large Language Models in Retrieval-Augmented Generation](https://mlsanity.com/paper/2309.01431/) (2023)
- [Evaluating Quantized Large Language Models](https://mlsanity.com/paper/2402.18158/) (2024)
- [A Comprehensive Evaluation of Quantization Strategies for Large Language Models](https://mlsanity.com/paper/2402.16775/) (2024)
- [Porting Large Language Models to Mobile Devices for Question Answering](https://mlsanity.com/paper/2404.15851/) (2024)

## Built on by (most cited first, 1 of 1)

- [Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop](https://mlsanity.com/paper/2610.15692/) (2026)

## Abstract (arXiv)

The integration of large language models (LLMs) into education offers significant potential to enhance accessibility and engagement, yet their high computational demands limit usability in low-resource settings, exacerbating educational inequities. To address this, we propose an offline Retrieval-Augmented Generation (RAG) pipeline that pairs a small language model (SLM) with a robust retrieval mechanism, enabling factual, contextually relevant responses without internet connectivity. We evaluate the efficacy of this pipeline using domain-specific educational content, focusing on biology coursework. Our analysis highlights key challenges: smaller models, such as SmolLM, struggle to effectively leverage extended contexts provided by the RAG pipeline, particularly when noisy or irrelevant chunks are included. To improve performance, we propose exploring advanced chunking techniques, alternative small or quantized versions of larger models, and moving beyond traditional metrics like MMLU to a holistic evaluation framework assessing free-form response. This work demonstrates the feasibility of deploying AI tutors in constrained environments, laying the groundwork for equitable, offline, and device-based educational tools.