Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems
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, behavioral, and alignment safety and propose the Reward Hacking Severity Index (RHSI) to quantify misalignment between proxy rewards and genuine learning. We evaluate the framework in a controlled simulation of an AI tutoring environment with 120 sessions across four conditions and three learner profiles, totaling 18{,}000 interactions. Results show that an engagement-optimized agent systemat...
| Authors | Oluseyi Olukola, Nick Rahimi |
|---|---|
| Primary category | cs.AI |
| Published | 5 April 2026 |
| Last updated at source | 5 April 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.