AI summaryⓘ
The authors present a system called the Actuarial Action Interface (AAI) to manage and control the risky actions taken by autonomous AI agents, like making refunds or changing databases. AAI assigns a cost to each action based on fixed rules and limits how much can be spent, ensuring the AI doesn't cause too much unintended damage. They also introduce the Authority Frontier, a way to measure how much freedom the AI has under different budget limits. The authors tested this system across multiple environments and found that it helps prevent losses by adjusting how much authority each AI model gets. Overall, their work offers a new method to safely evaluate and govern autonomous AI actions in various settings.
Autonomous AI agentsActuarial Action InterfaceRuntime contractRisk mappingReserve capital budgetAuthority FrontierDeterministic protocolsAction taxonomyReplay determinismUnderwriting
Abstract
Autonomous AI agents increasingly issue side-effect-bearing actions: database mutations, refunds, payments, external commitments. We propose the Actuarial Action Interface (AAI), a deterministic runtime contract that prices each such action against a contractually fixed safe default under a time-consistent risk mapping, and gates execution against a per-boundary reserve capital budget. We then develop the Authority Frontier, an evaluation primitive measuring how much autonomous authority the runtime releases at each level of reserve capital. The framework provides (i) a deterministic quote-bind-commit protocol with toll-bounded capability tokens; (ii) a universal seven-class action taxonomy mapping heterogeneous tool calls to comparable authority units; (iii) replay determinism and pathwise reserve coverage under alpha-spending; (iv) cross-domain normalization via full reserve demand C_full and capital metrics Capital@k. We instantiate AAI across four agentic environments (database mutation, customer-service refund, and the public tau-bench retail and airline tool-use traces) and report a live Postgres panel in which three Azure-hosted models propose actions through the same contract. The frontier exhibits a common low-reserve refusal and intermediate-release pattern across domains, with saturation only where the budget grid reaches full reserve demand; required reserve capital varies by 22x (Capital@50 from 289 to 6457). The framework does not force domains into the same shape; it surfaces each domain's actuarial geometry. In the live panel the contract prevents realized loss across all three models at low budget while differing in underwriting persistence under denial: model identity is an actuarial underwriting variable. The contribution is a benchmark-ready evaluation framework for runtime actuarial control of autonomous-agent side effects.