In Unite AI, Prof. Alexander Fouirnaies and coauthors warn that multi-agent AI systems can mistake consensus for accuracy. Agents can herd toward shared but unsupported answers, raising questions about systems that reward evidence, not just agreement. har.rs/4i09CrL
har.rs
When AI Agents Follow the Crowd: The Hidden Risk in Multi-Agent Consensus
A room full of agreeing AI agents can look reassuring. One proposes an answer, another checks it, and several more endorse the conclusion. But how many of those agents actually checked the underlying ...