The gain from misreporting to your own proxy equals the proxy's within-range regret, so honest reporting is optimal exactly when the proxy already plays the best reachable action; guardrails then face a binding–truthful–capability trilemma.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GT 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Is Delegated Play Truthful? Within-Range Regret and the Trilemma of Aligned Delegation
The gain from misreporting to your own proxy equals the proxy's within-range regret, so honest reporting is optimal exactly when the proxy already plays the best reachable action; guardrails then face a binding–truthful–capability trilemma.