Tag
humans& releases &Tutor, an AI model trained to teach by training against Persimmon as a simulated learner, achieving state-of-the-art results on the TutorMoments benchmark and outperforming frontier models like Claude Sonnet 5.5 and GPT-6 Astra under plain prompting.
MCAT Tutor is an AI agent that helps prepare for the MCAT by teaching scientific reasoning and passage analysis, adapting to individual user needs for personalized coaching.
The article presents five GitHub-based skills for AI agents, enabling them to function as tutors, manage YouTube workflows, design platforms, add guardrails, and assist founders with daily tasks.
DeepTutor is an open-source, AI-driven learning workspace that integrates tutoring, problem-solving, quizzes, and more, offering a lifelong personalized learning experience.
This article critiques the failure of Khanmigo, an AI tutoring chatbot, arguing that its design as a 'teaching by telling' tool was inherently flawed, contrasting it with effective learning through making and exploration.
ByteDance is expanding its AI education app Gauth with AI-generated animations to walk students through problem-solving, raising questions about whether such tools genuinely improve comprehension or merely create an illusion of learning.
This paper presents a pre-registered audit of whether LLM-judged helpfulness can reliably distinguish answer-giving from pedagogical guidance in AI tutors. The authors find that general-purpose helpfulness is not a dependable pedagogy signal, recommending pedagogy-targeted rubrics and deterministic process measures instead.
HKU has open-sourced an AI personalized tutoring tool called DeepTutor, which supports multiple modes, a memory system, and local model deployment, and has already earned 25k stars on GitHub.
MIT has launched the MIT4America Calculus Project to provide remote calculus tutoring to students in underresourced US high schools, addressing the lack of calculus access in nearly half of American high schools.
This paper proposes an adaptive, subject-aware prompt routing framework for LLM-based high-school tutoring, using 14 pedagogical features to switch strategies. A/B testing with 359 students shows improved efficiency and conversion rates over static baselines.
This paper proposes a system that combines a prerequisite knowledge graph with a PPO-based policy to structure Socratic tutoring with LLMs, showing improved student mastery and efficiency over heuristic and frontier model baselines.
A Stanford Law School study found that law professors rated LLM-generated answers higher than peer answers in a blinded evaluation of short-answer tutoring in contracts courses, with LLMs winning 75.33% of comparisons and being flagged as harmful less often.
Introduces EduAgentBench, a source-grounded benchmark for evaluating tutor agents across professional pedagogical judgment, multi-turn tutoring, and autonomous teaching workflow execution. Evaluations on frontier models show they still fall short of professional teaching standards in situated tutoring and workflow tasks.