---
source_url: https://arxiv.org/abs/2604.04237
ingested: 2026-05-08
sha256: 405026ca9110fd1b912233399b447718c35e8ab554eaa85bb9ecebee1d785ffd
---

# Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems

**Authors:** Oluseyi Olukola, Nick Rahimi
**Published:** 2026-04-05
**Categories:** cs.AI, cs.CY, cs.LG
**arXiv:** https://arxiv.org/abs/2604.04237
**PDF:** https://arxiv.org/pdf/2604.04237

## Abstract

Reinforcement learning (RL) is increasingly used to personalize instruction in intelligent tutoring systems, yet the field lacks a formal framework for defining and evaluating pedagogical safety. We introduce a four-layer model of pedagogical safety for educational RL comprising structural, progress...