arxiv
PublishedApril 7, 2026 at 4:00 AM
—neutral
Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems
Publisher summary· verbatim
arXiv:2604.04237v1 Announce Type: cross 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
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivBringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning7harxivSubagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks7harxivDistribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts7harxivIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning7hThe Bubble Brief
WEEKLYRead education insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗