Value-Aware Multiagent Systems
By: Nardine Osman
This paper introduces the concept of value awareness in AI, which goes beyond the traditional value-alignment problem. Our definition of value awareness presents us with a concise and simplified roadmap for engineering value-aware AI. The roadmap is structured around three core pillars: (1) learning and representing human values using formal semantics, (2) ensuring the value alignment of both individual agents and multiagent systems, and (3) providing value-based explainability on behaviour. The paper presents a selection of our ongoing work on some of these topics, along with applications to real-life domains.
Similar Papers
Rethinking How AI Embeds and Adapts to Human Values: Challenges and Opportunities
Artificial Intelligence
AI learns to change its mind with our values.
Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectives
Artificial Intelligence
Makes AI agents follow human rules and values.
Understanding the Process of Human-AI Value Alignment
Computers and Society
Helps AI understand and follow human values.