DeepTutor, developed by Bingxi Zhao, is a fully open-source agentic framework that unifies citation-grounded problem tutoring with difficulty-calibrated question generation. The system couples static knowledge grounding with dynamic learner memory to adapt interactions to individual students. Evaluations on the introduced TutorBench benchmark show DeepTutor improves personalized metrics by 10.8% on average and strengthens general agentic reasoning across five backbone models by 29.4%.
No score is assigned. Sources and their independence are shown in the citation chain below.