English

Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI

Artificial Intelligence 2024-11-19 v1 Computers and Society Machine Learning

Abstract

Pluralistic alignment is concerned with ensuring that an AI system's objectives and behaviors are in harmony with the diversity of human values and perspectives. In this paper we study the notion of pluralistic alignment in the context of agentic AI, and in particular in the context of an agent that is trying to learn a policy in a manner that is mindful of the values and perspective of others in the environment. To this end, we show how being considerate of the future wellbeing and agency of other (human) agents can promote a form of pluralistic alignment.

Keywords

Cite

@article{arxiv.2411.10613,
  title  = {Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI},
  author = {Parand A. Alamdari and Toryn Q. Klassen and Rodrigo Toro Icarte and Sheila A. McIlraith},
  journal= {arXiv preprint arXiv:2411.10613},
  year   = {2024}
}

Comments

Pluralistic Alignment Workshop at NeurIPS 2024

R2 v1 2026-06-28T20:01:57.944Z