Modeling Descriptive Norms in Multi-Agent Systems: An Auto-Aggregation PDE Framework with Adaptive Perception Kernels

2026-01-10

arXiv.org

AI Summary

This study investigates the dynamic emergence and evolution of descriptive norms in autonomous multi-agent systems, with a focus on norm convergence and the spontaneous appearance of norm violations. The authors propose a self-aggregation model grounded in nonlocal transport partial differential equations, representing opinion popularity as a continuous distribution and capturing norm formation through adaptive perception kernels and external potential fields. This approach transcends conventional Bayesian belief inference frameworks by enabling top-down constraints, bottom-up reconstruction, and fully autonomous interactions that yield multi-centered norm structures. Experiments on real-world COVID-19 clinical datasets demonstrate that top-down mechanisms accelerate norm convergence, bottom-up strategies reconstruct data-consistent norms via a “violation–recoupling” process, and fully autonomous interactions give rise to multi-centered norm structures independent of the underlying data distribution.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Learning Human Values and Preferences

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

This paper presents a PDE-based auto-aggregation model for simulating descriptive norm dynamics in autonomous multi-agent systems, capturing convergence and violation through non-local perception kernels and external potential fields. Extending classical transport equations, the framework represents opinion popularity as a continuous distribution, enabling direct interactions without Bayesian guessing of beliefs. Applied to a real-world COVID-19 dataset from a major medical center, the experimental results demonstrate that: when clinical guidelines serve as a top-down constraint mechanism, it effectively generates convergence of novel descriptive norms consistent with the dataset; in the bottom-up experiment, potential field guidance successfully promotes the system's reconstruction of descriptive norms aligned with the dataset through violation-and-recoupling; whereas fully autonomous interaction leads to the emergence of multi-centric normative structures independent of the dataset.

Problem

• descriptive norms
• multi-agent systems
• norm dynamics
• convergence
• violation

Innovation

• descriptive norms
• multi-agent systems
• partial differential equations (PDE)
• non-local perception kernels
• potential fields