AI RESEARCH
What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty
arXiv CS.LG
•
ArXi:2603.02491v2 Announce Type: replace As artificial agents become increasingly capable, what internal structure is *necessary* for an agent to act competently under uncertainty? Classical results show that optimal control can be *implemented* using belief states or world models, but not that such representations are required.