DeepTutor: Towards Agentic Personalized Tutoring

TL;DR

DeepTutor is an open-source framework that enhances personalized tutoring using LLMs by integrating citation-grounded problem solving with dynamic learner modeling, improving adaptation and reasoning.

Contribution

It introduces a hybrid personalization engine and a comprehensive benchmark for evaluating agentic personalized tutoring with LLMs.

Findings

DeepTutor improves personalized metrics by 10.8% on average.

Strengthens agentic reasoning across five backbone models by 29.4%.

Supports adaptive learning workflows, interactive books, and multi-channel tutoring.

Abstract

Education is one of the most promising real-world applications for Large Language Models (LLMs). However, current LLMs rely on static pre-training knowledge and lack adaptation to individual learners, while existing RAG systems fall short in delivering personalized, guided feedback. To bridge this gap, we present DeepTutor, a fully open-source agentic framework that unifies citation-grounded problem tutoring with difficulty-calibrated question generation. A hybrid personalization engine couples static knowledge grounding with dynamic learner memory, continuously adapting each interaction to the student's evolving needs. The same personalization substrate further extends to adaptive learning workflows, interactive books, and proactive multi-channel tutoring agents. To evaluate personalized tutoring, we introduce TutorBench, an interactive benchmark incorporating customized learner profiles grounded in university-level curricula across five domains. We further propose an LLM-based first-person interactive evaluation protocol that conducts assessments via a profile-driven student simulator. Complementary evaluations on established benchmarks, supported by human-alignment and ablation studies, confirm the framework's robustness and general utility. Results show that DeepTutor improves personalized metrics by 10.8\% on average and strengthens general agentic reasoning across five backbone models by 29.4\%.