What Do We Need for an Agentic Society?

2026-04-04

AI Summary

This study addresses coordination failures in multi-agent systems caused by misjudgment, deadlocks, or adversarial attacks by proposing a novel paradigm: the “agent society,” composed of everyday objects endowed with autonomy, reactivity, proactiveness, and social capabilities that collectively achieve intelligence surpassing individual capacities. The work systematically identifies three core challenges inherent to agent societies—what to share, how to assess, and when to act—and integrates contextual modeling, trust mechanisms, and distributed decision-making frameworks to analyze failure modes and mitigation strategies. Empirical validation through scenarios involving adolescent bullying and depression demonstrates the paradigm’s practical potential and highlights critical challenges, thereby establishing a new research agenda for multi-agent coordination.

Abstract

Thirty years ago, Wooldridge and Jennings defined intelligent agents through four properties: autonomy, reactivity, pro-activeness, and social ability. Today, advances in AI can empower everyday objects to become such intelligent agents. We call such objects agentic objects and envision that they can form an agentic society: a collective agentic environment that perceives patterns, makes judgments, and takes actions that no single object could achieve alone. However, individual capability does not guarantee coordination. Through an illustrative scenario of a teenager experiencing bullying and depression, we demonstrate both the promise of coordination and its failure modes: false positives that destroy trust, deadlocks that prevent action, and adversarial corruption that poisons judgment. These failures reveal open questions spanning three phases: what to share, how to judge, and when to act. These questions chart a research agenda for building agentic societies.

Problem

• agentic society
• coordination
• intelligent agents
• trust
• collective action

Innovation

• agentic society
• intelligent agents
• coordination failures
• collective judgment
• multi-agent systems