RESEARCH

Trust Between AI Agents: Measuring Formation, Breakage, and Recovery, with Implications for Governing Multi-Agent Systems

ArXiv cs.AI · Tue, 16 Jun 2026 04:00:00 GMT

arXiv:2606.14923v1 Announce Type: new Abstract: As language-model agents increasingly work in teams, each agent must decide how much to trust its teammates. Yet we lack a standard way to measure trust between AI agents. We propose a behavioral measure based on costly verification

Read original source Discuss with A.S.I.S