Aligning Institutional Power and Operational Ability
This paper proposes a formal framework for designing normatively aligned multi-agent systems.
The paper introduces a novel formal framework for normative alignment in multi-agent systems, which is a new approach compared to prior work.
Before reading this…
Applications
- →Designing socially sustainable AI systems
- →Avoiding normative pitfalls in multi-agent systems
To understand this paper, make sure you know these concepts first:
- Understanding of multi-agent systemsfind papers →
- Knowledge of normative alignmentfind papers →
Abstract
More Like ThisTo be socially sustainable, Agentic AI systems require normative designs that align responsibilities with the ability to fulfil them. Identifying incongruences such as unsatisfiable expectations or privilege escalation is crucial in avoiding normative pitfalls. In this study, we discuss design dimensions suitable for describing multi-agent systems in light of this norm-ability alignment requirement. We propose a formal framework centred on process-oriented modelling and institutional power for the analysis of a given normatively relevant process, discuss strategies for repairing it, and elaborate on how the symmetrical relation between operational process and institutional state affects the lifecycle of normative positions.