Agentic Societies Need a Social Harness

2026-09-15

AI Summary

研究针对AI代理社会中的协作失败问题，提出了一种社会约束机制，通过分层架构预防故障、检测异常消息并支持事后调查。

Abstract

An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries, on behalf of different principals whose objectives may only partially align. We show experimentally that in agentic societies even honest, competent agents often fail to reach satisfactory outcomes with existing harnesses and messaging primitives, and that faulty or malicious agents can stall collaboration, influence outcomes, and pursue other harmful goals by exploiting vulnerabilities in communication (``speech''). We argue that agentic societies need a \emph{social harness} for inter-agent interactions, in addition to each agent's \emph{personal harness}, which manages its private context and communication with its principal. We propose a layered architecture for social harnesses which (i) prevents classes of failures outright, (ii) enables agents to detect invalid messages at runtime, and (iii) supports post-facto investigation and consequences, and highlight directions for future research to realize these capabilities.

Problem

• agentic societies
• AI agents
• trust boundaries
• communication vulnerabilities
• social harness

Innovation

• social harness
• agentic society
• inter-agent interaction
• communication vulnerabilities