发表机构
United Nations University Institute in Macau; AI Singapore; Data Science for Social Impact Lab, University of Pretoria; African Institute for Data Science and AI, University of Pretoria（联合国大学澳门研究所; 新加坡人工智能研究院; 比勒陀利亚大学社会影响数据科学实验室; 比勒陀利亚大学非洲数据科学与人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有决策支持方法仅输出单一共识结果的局限，提出多智能体系统KITA AI，让基于不同利益相关方角色的大语言模型智能体开展政策审议，输出多元立场理据与不收敛结果，辅助决策者理解政策权衡与影响。
AI 中文摘要
应对紧迫社会与环境挑战的公共政策需明确考量受影响利益相关方多元且往往相互冲突的观点。尽管计算决策支持方法越来越多地能针对不同人类价值体系给出建议，但它们仍倾向于输出单一的共识驱动结果。我们提出KITA AI，这是一个模块化系统，其中多个大语言模型智能体分别基于不同人口特征的利益相关方角色与概念框架，针对政策场景展开审议。KITA AI的目标不仅是告知优选政策方案，还能自动揭示哪些群体会受该场景影响，并为决策者提供每种立场背后的理据与量化指标。KITA AI将不收敛视为一等可解释输出，帮助政策制定者更好地理解所讨论政策的权衡关系与人文影响。
英文摘要
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.
