Fair Agents: Balancing Multistakeholder Alignment in Multi-Agent Personalization Systems

2026-05-04

AI Summary

This study addresses the challenges of conflicting objectives and fairness in multi-stakeholder personalized systems by proposing a multi-agent framework that integrates goal alignment, a social choice theory–driven fair aggregation mechanism, and stakeholder-centric evaluation. It represents the first systematic integration of multi-objective alignment, fair aggregation, and evaluation methodologies to establish a design paradigm for fairness-aware personalization. Leveraging large language model–based agents, the framework demonstrates effectiveness in a tourism scenario and explores its generalization potential in domains such as education and healthcare. The work also surveys existing datasets and core challenges pertinent to fairness evaluation in such systems.

Abstract

LLM agents are increasingly used for personalization due to their ability to communicate directly with users in natural language, integrate external knowledge bases, and negotiate with other (possibly human) agents. Especially in multistakeholder AI systems with multiple distinct objectives, LLM agents are used to independently optimize for each stakeholder's goals. Here, stakeholder alignment is essential to identify and map these goals to provide LLM agents with quantifiable objectives. Plus, the way in which the outputs of the LLM agents are aggregated is fundamental to ensuring fair outcomes for all agents and, therefore, stakeholders. In this work, we identify open research challenges and propose a conceptual framework for designing fair multi-agent multistakeholder personalization systems that balance competing stakeholder objectives. Our framework integrates (i) methods to align stakeholder objectives and LLM agents, (ii) aggregation strategies, e.g., based on social choice theory, to form fair collective decisions, and (iii) stakeholder-centric evaluation procedures for both individual and collective agent behavior. We showcase our framework through a tourism use case and discuss possible applications in other domains, such as education and healthcare. Finally, we discuss domain-specific fairness tensions and review datasets for evaluating multistakeholder fairness and multi-agent personalization systems.

Problem

• multi-agent systems
• personalization
• multistakeholder fairness
• LLM agents
• fairness

Innovation

• multi-agent systems
• multistakeholder fairness
• LLM personalization
• social choice theory
• stakeholder alignment