The integration of Large Language Models into Intelligent Tutoring Systems pre-sents significant challenges in aligning with diverse and often conflicting values from students, parents, teachers, and institutions. Existing architectures lack for-mal mechanisms for negotiating these multi-stakeholder tensions, creating risks in accountability and bias. This paper introduces the Advisory Governance Layer (AGL), a non-intrusive, multi-agent framework designed to enable distributed stakeholder participation in AI governance. The AGL employs specialized agents representing stakeholder groups to evaluate pedagogical actions against their spe-cific policies in a privacy-preserving manner, anticipating future advances in per-sonal assistant technology that will enhance stakeholder value expression. Through a novel policy taxonomy and conflict-resolution protocols, the frame-work provides structured, auditable governance advice to the ITS without altering its core pedagogical decision-making. This work contributes a reference architec-ture and technical specifications for aligning educational AI with multi-stakeholder values, bridging the gap between high-level ethical principles and practical implementation.
@article{arxiv.2510.23245,
title = {Multi-Stakeholder Alignment in LLM-Powered Collaborative AI Systems: A Multi-Agent Framework for Intelligent Tutoring},
author = {Alexandre P Uchoa and Carlo E T Oliveira and Claudia L R Motta and Daniel Schneider},
journal= {arXiv preprint arXiv:2510.23245},
year = {2025}
}