The Ethereum Foundation (EF) deployed coordinated AI agents against critical components of blockchain infrastructure, examining system software, cryptographic code, and smart contracts. "Agents finding bugs was no surprise. The surprise was how little effort was needed to find them and how much was required to separate real bugs from those that only appeared real," EF stated. The team abandoned a single large AI agent model, instead using several specialized systems working in parallel against a single repository. "The time previously spent on forming and testing hypotheses is now spent on evaluating them at scale: building an oracle, triage, maintaining a list of known issues, and disclosure," EF wrote. A publicly disclosed example is the vulnerability CVE-2026-34219 in the Rust implementation of libp2p gossipsub, which allowed remote triggering of a process crash when processing a specially crafted PRUNE message with nearly maximum backoff value. EF did not disclose how many real bugs the agents found. Journalists from The Block noted that most candidates found by AI agents were false positives, duplicates, or issues outside the scope of the review. According to the team, AI agents are less effective.