G. Prencipe

This paper proves that, given the necessary (and sufficient) number of agents, a team of oblivious agents can perpetually explore the safe nodes without any prior knowledge of the network or the team, without agent or node IDs, under semi-synchronous schedulers, and provides an algorithm that enables agents to safely explore the network and terminate.

Confidence-ranked auditing of LLM agents can backfire, with miscalibration thresholds rising as audit budgets shrink, leading to worse outcomes than random selection.