Social-harness study finds cross-owner agents fail even when honest

University of Washington tests agents that schedule meetings across separate owners and trust boundaries. Honest-agent success often falls as group size grows; one configuration drops from 90% to 0% when moving from one to seven participants. Malicious agents exploit unverified claims, social pressure and fragmented calendar disclosure despite model safety training. The paper proposes a five-layer social harness for identity, ordered communication, action guards, protocol norms and governance.

For multi-party agent systems, transport protocols such as A2A are connectivity, not a trust model. Messages need provenance, authority checks, task-state rules and auditable consequences outside the model. The experiments cover scheduling rather than open-ended enterprise work, so the proposed stack is a design target, not a finished standard.