602 citations · 678 across the 8 of their papers we have counts for
3 papers · 1 filter
Human Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent Failures
Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
When an LLM agent misbehaves, a human steps in, and that intervention is usually discarded or replayed as training data. We treat it instead as a measurement: a label pointing at t…
Safe Exploration of Arbitrary Dynamic Dangerous Networks
Caterina Feletti, Paola Flocchini, Giuseppe Prencipe +1
Given a team of agents on the nodes of a graph-based network, the exploration problem requires each node to be visited by at least one agent. In the classical distributed setting o…
One Human, Agents: Audit-Budget Allocation for LLM Agent Fleets under Miscalibrated, Correlated Confidence
Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
A single human must audit LLM agents under a budget of audits per round, guided by self-reported confidence that may be adversarially miscalibrated and by correlated…