Rohan Paul (@rohanpaul_ai) · 10/20/2026, 01:04:38
Salesforce Study Reveals Lack of Cross-Verification in Multi-Agent Systems
A new Salesforce paper reveals that AI agents representing different parties fail to verify each other's claims by default, causing teams to inherit errors from their weakest agent. Through over 2,500 cross-sandbox sessions, the study cataloged 20 failure modes and emphasizes the need for protocol-level verification checks and party-specific scoring.
SOURCE COVERAGEFull Original Report
Rohan Paul (@rohanpaul_ai) · 2026-10-19 17
New Salesforce paper finds that agents acting for different parties never verify each other's claims unprompted, so teams inherit their weakest agent's errors.
Agents increasingly coordinate with agents that represent other people or companies, each with private files, tools, and goals. Existing failure studies assume 1 orchestrator or a shared workspace.
They ran over 2,500 agent-to-agent sessions across 488 scenarios, using Claude Code, Codex, and Cursor in separate sandboxes. They catalogued 20 failure modes from the traces.
No agent re-fetched a document to test a peer's factual claim, and agents contacted peers mainly when the prompt told them to. In 1 service-level dispute, a $24,000 settlement passed all 10 outcome checks while the vendor agent leaked confidential details.
If your agent talks to outside agents, build checks into the protocol and score each agent against the party it serves, not the team result.
