Problem
Research questions and friction points this paper is trying to address.
pluralistic policy deliberation
multi-stakeholder perspectives
computational decision-support
non-convergence
value pluralism
KITA AI: A Multi-Agent LLM System for Pluralistic Policy Deliberation
🤖 AI Summary
This study addresses the challenge of reconciling conflicting stakeholder interests and the limitations of single-consensus approaches in public policymaking. We propose a modular multi-agent large language model (LLM) system that simulates policy debates among diverse stakeholders based on demographic profiles, automatically identifying affected populations and providing quantitative evidence. The core innovation lies in treating non-convergence as an interpretable, first-class output that explicitly surfaces policy trade-offs and human impacts, rather than forcing a singular consensus. By delivering a multidimensional analytical framework that integrates positional reasoning with quantitative metrics, the system equips policymakers with enhanced insight into policy trade-offs and their deeper societal implications.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-Agent LLM System
Pluralistic Policy Deliberation
Stakeholder Personas
Non-convergence
Explainable Output
🔎 Similar Papers
No similar papers found.
