arXiv Machine Learning
PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
3d ago
Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
arXiv:2605.30051v2 Announce Type: replace Abstract: A key part of developing large language model (LLM)-powered, automated tutoring tools is student simulation, i.e., using LLMs to role-play as stude...
arXiv AI
Aug 26
UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models
The paper introduces UCO, a multi‑turn interactive reinforcement learning method designed to improve adaptive teaching with large language models. UCO employs two reward functions—Progress Reward to gauge genuine cognitive advancement and Scaffold Reward to keep instruction within each student’s Zone of Proximal Development. Experiments on BigMath and MathTutorBench show UCO outperforming 11 baseline models and matching advanced closed‑source systems.
arXiv AI
Jun 9
MC-CPO: Mastery-Conditioned Constrained Policy Optimization for Pedagogically Safe Intelligent Tutoring Systems
arXiv:2604. 04251v2 Announce Type: replace Abstract: Intelligent tutoring systems increasingly rely on reinforcement learning to personalise instruction, yet optimising for observable engagement signals can systematically decouple learner activity from genuine knowledge acquisition.
arXiv AI
Jul 10
DeepTutor: Towards Agentic Personalized Tutoring
arXiv:2604. 26962v3 Announce Type: replace-cross Abstract: Education is one of the most promising real-world applications for Large Language Models (LLMs).
arXiv AI
Aug 19
Effective Personalized AI Tutors via LLM-Guided Reinforcement Learning
The paper presents a tutoring platform that combines a generative AI chatbot with a reinforcement learning algorithm to adaptively sequence practice problems for students learning Python. In a five‑month field study across ten high schools, the adaptive sequencing improved unassisted final exam performance by 0.15 standard deviations, with mediation analysis indicating that higher engagement drove the gains. The study demonstrates that signals from student‑chatbot interactions can be leveraged to personalize and optimize learning at scale.
arXiv AI
Jun 10
SocraticPO: Policy Optimization via Interactive Guidance
arXiv:2606. 09887v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness.