KITA AI models diverse views to explain public policy trade offs
KITA AI: A Multi-Agent LLM System for Pluralistic Policy Deliberation
Computers and Society
Summary
Public policies often affect different groups of people in many ways, and their views can conflict. The authors present KITA AI, a system where multiple AI agents each represent a different group’s perspective to discuss policies. Instead of forcing agreement, KITA AI highlights where opinions differ and why, showing decision makers the reasons and impacts behind each view. This helps policymakers understand trade-offs and human effects more clearly.
What this means in practice
- •For policy analysts: Provide balanced views from multiple stakeholder perspectives to clarify policy trade-offs and impacts before decisions.
- •For corporate social responsibility teams: Use multi-agent deliberation to anticipate diverse community impacts of company policies and improve stakeholder engagement.
Authors
Arnau Mayoral-Macau, Jiaqi Lai, Manala Tyobeka, Vukosi Marivate, William Chandra Tjhi, Georgina Curto
Abstract
Public policies addressing urgent social and environmental challenges need to explicitly consider the diverse, often conflicting perspectives of the affected stakeholders. Despite computational decision-support approaches increasingly offering recommendations across diverse human value systems, they still tend to deliver a single consensus-driven outcome. We present KITA AI, a modular system in which multiple large language model agents, each grounded in distinct demographic stakeholder personas and conceptual frameworks, deliberate on policy scenarios. The objective of KITA AI is not merely to inform about a preferred policy proposal, but also to automatically surface who is affected by the scenario and provide decision-makers with the rationales and quantitative indicators behind each position. KITA AI treats non-convergence as a first-class explainable output, enabling policymakers to better understand the trade-offs and human impacts of the policies being discussed.