# Empowering Private Tutoring by Chaining Large Language Models

arXiv: https://arxiv.org/abs/2309.08112 · HTML: https://mlsanity.com/paper/2309.08112/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 54 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)

## Built on by (most cited first, 9 of 9)

- [Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation](https://mlsanity.com/paper/2407.08940/) (2024)
- [History, Development, and Principles of Large Language Models-An Introductory Survey](https://mlsanity.com/paper/2402.06853/) (2024)
- [LLM-powered Multi-agent Framework for Goal-oriented Learning in Intelligent Tutoring System](https://mlsanity.com/paper/2501.15749/) (2025)
- [From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents](https://mlsanity.com/paper/2409.03512/) (2024)
- [Scaffolding Language Learning via Multi-modal Tutoring Systems with Pedagogical Instructions](https://mlsanity.com/paper/2404.03429/) (2024)
- [Is the Lecture Engaging for Learning? Lecture Voice Sentiment Analysis for Knowledge Graph-Supported Intelligent Lecturing Assistant (ILA) System](https://mlsanity.com/paper/2408.10492/) (2024)
- [Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents](https://mlsanity.com/paper/2510.17491/) (2025)
- [GuideAI: A Real-time Personalized Learning Solution with Adaptive Interventions](https://mlsanity.com/paper/2601.20402/) (2026)
- [From Memorization to Creation: Evaluating the Cognitive Depth of LLM-Generated Educational Questions](https://mlsanity.com/paper/2606.18257/) (2026)

## Abstract (arXiv)

Artificial intelligence has been applied in various aspects of online education to facilitate teaching and learning. However, few approaches has been made toward a complete AI-powered tutoring system. In this work, we explore the development of a full-fledged intelligent tutoring system powered by state-of-the-art large language models (LLMs), covering automatic course planning and adjusting, tailored instruction, and flexible quiz evaluation. To make the system robust to prolonged interaction and cater to individualized education, the system is decomposed into three inter-connected core processes-interaction, reflection, and reaction. Each process is implemented by chaining LLM-powered tools along with dynamically updated memory modules. Tools are LLMs prompted to execute one specific task at a time, while memories are data storage that gets updated during education process. Statistical results from learning logs demonstrate the effectiveness and mechanism of each tool usage. Subjective feedback from human users reveal the usability of each function, and comparison with ablation systems further testify the benefits of the designed processes in long-term interaction.