When Is Delegated Play Truthful? Within-Range Regret and the Trilemma of Aligned Delegation

Jul 17, 2026

A new preprint introduces 'within-range regret' as a key concept for understanding when it is optimal for a principal to honestly communicate their preferences to an automated proxy, such as a language model or autobidder. The authors prove a trilemma: no guardrail on the proxy can be simultaneously binding, truthful, and capability-preserving. Empirical tests on production language models show that honest reporting often leaves surplus unclaimed, which can be recovered by strategically inflating the report.

Why it matters: This work formalizes the incentive structure behind prompt engineering and jailbreaking, revealing fundamental trade-offs in aligning AI proxies.

Full story at: arXiv Multiagent Systems ↗