Simulated Norms: An Ontological Analysis of Normative Role Design in Multi-Agent LLM Systems
Work-in-progress master's thesis
Normative role design for LLM agents is happening through rapid, experimental, and unsystematic prompt engineering. Developers, researchers, and systems designers are embedding ethical assumptions into agents' roles through trial-and-error, often focusing on outcomes rather than coherent principles. We lack a systematic vocabulary for describing the kinds of norms embedded in LLM agents.
Analyze around twenty simulation experiments to construct a preliminary ontology of normative role design in Multi-Agent systems (MAS).
  1. AI agents are being deployed in critical domains: From energy grids and supply chains to healthcare and education.
  2. Design choices encode norms: How we prompt and structure agents shapes their decision-making and societal impact.
  3. Scale amplifies risk: These systems operate at massive scale, affecting millions of users and real-world outcomes.
Main Research Question
What types of normative roles are operationalized across different applications of multi-agent systems?
Approach: Constructing an ontology using qualitative content analysis.
Data: ~20 multi-agent LLM simulation papers and their GitHub repositories.
Units of Analysis:
  1. System Prompts (core object) — Natural Language Role instructions embedded in model's code base
  2. Simulation Papers — Contextual data: simulation domain, architecture, evaluation, outcomes
Analytical Process:
1. Systematic Selection – Apply purposive selection and inclusion criteria to collect top papers in the field
2. Inductive Coding – Identify and tag system prompts + context
3. Ontology Construction – Build a structured map of role types, mechanisms, intentions and relationships
Three normative ethical theories guide the analysis:
Deontological
rules, duties, obligations
Consequentialist
outcomes, utility, optimization
Virtue Ethics
character traits, social roles
Based on Woodgate & Ajmeri (2024), Macro Ethics Principles for Responsible AI Systems
Expected Contribution
Ontology of Normative Role Design · Map of Prompts, Norms, and Behaviors · Risk & Inconsistency Detection Lens · Guidance for Developers & Policymakers
Deliverables: Thesis · Conceptual ontology · Briefs · Workshops · Academic articles