arXiv cs.AI· Tapan Chugh, Vidushi Singh, Krish Jain, Arvind Krishnamurthy, Ratul Mahajan·· 6 小时前AI 评分41
Agentic 智能体社会需要社交层 Harness（Social Harness）
Agentic Societies Need a Social Harness
AI 导读
一篇 arXiv 论文通过实验证明，在由 AI 智能体组成的 agentic society 中，即使诚实且有能力的前沿智能体，用现有 harness 和消息原语也常无法达成满意结果；故障或恶意智能体可利用通信漏洞完全阻塞进程、影响结果并追求有害目标。
正文 · 原文
Abstract:An agentic society is a collection of AI agents that coordinate autonomously across trust boundaries on behalf of different principals. We show experimentally that in such societies even honest, competent agents often fail to reach satisfactory outcomes when using current harnesses and messaging primitives; and faulty or malicious agents can completely stall progress, influence outcomes, and pursue harmful goals by exploiting communication vulnerabilities. We argue that agentic societies need a \emph{social harness}. Unlike a \emph{personal harness}, which manages private context and communication with the principal, a social harness manages interactions with other agents. We propose a layered architecture for social harnesses which (i) prevents classes of communication failures outright, (ii) enables agents to detect invalid messages, and (iii) supports post-facto investigation and consequences.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI) |
| Cite as: | arXiv:2609.17527 [cs.MA] |
| (or arXiv:2609.17527v2 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2609.17527 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1145/3847290.3859974
DOI(s) linking to related resources |
Submission history
From: Tapan Chugh [view email]
[v1]
Tue, 15 Sep 2026 17:57:27 UTC (722 KB)
[v2]
Sat, 24 Oct 2026 03:56:53 UTC (721 KB)
来源：arXiv cs.AI · arxiv.org