AI RESEARCH
Preserving Disagreement: Architectural Heterogeneity and Coherence Validation in Multi-Agent Policy Simulation
arXiv CS.AI
•
ArXi:2604.26561v1 Announce Type: cross Multi-agent deliberation systems using large language models (LLMs) are increasingly proposed for policy simulation, yet they suffer from artificial consensus: evaluator agents converge on the same option regardless of their assigned value perspectives. We present the AI Council, a three-phase deliberation framework, and conduct 120 deliberations across two policy scenarios to test two interventions.