When Does Randomized Oversight Align AI Agents That Can Conceal?

arXiv:2609.38262 · econ.TH, cs.AI · Submitted 2026-09-29 · Read on arXiv

econ.TH, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• AI Agents — 1× in this paper · explained in 2 episodes

Related papers

• Information Design for Differential Privacy
• Expectation-enforcing strategies for repeated games
• Robust Trust
• No Screening is More Efficient with Multiple Objects