What Do We Need for an Agentic Society?
This work addresses the problem of ensuring effective coordination among AI-powered agents in everyday environments, which is incremental as it builds on existing agent definitions to identify failure modes and propose future research directions.
The paper tackles the challenge of coordinating intelligent agents in an 'agentic society' to achieve collective goals, demonstrating through a scenario that failures like false positives, deadlocks, and adversarial corruption can occur, and it outlines a research agenda to address these issues.
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.