arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.25632cs.AIcs.LGq-fin.RM
收藏

为每个行动投保:自主AI代理运行时精算控制的权威边界框架

Insuring Every Action: An Authority Frontier Framework for Runtime Actuarial Control of Autonomous AI Agents

Department of Risk Management and Insurance(风险管理与保险系)

Hao-Hsuan Chen

AI总结:

提出精算行动接口(AAI)和权威边界框架,通过确定性运行时合约对自主AI代理的副作用行动进行定价、门控和评估,实现跨领域的精算控制与基准测试。

摘要:

自主AI代理越来越多地产生带有副作用的行动:数据库变更、退款、支付、外部承诺。我们提出精算行动接口(AAI),这是一个确定性的运行时合约,它在时间一致的风险映射下,对每个此类行动按照合约固定的安全默认值进行定价,并根据每个边界的储备资本预算门控执行。然后我们开发了权威边界,这是一种评估原语,用于衡量运行时在每个储备资本水平下释放的自主权威量。该框架提供:(i) 一个确定性的报价-绑定-提交协议,带有通行费限制的能力令牌;(ii) 一个通用的七类行动分类法,将异构工具调用映射到可比较的权威单位;(iii) 在alpha支出下的重放确定性和逐路径储备覆盖;(iv) 通过全储备需求C_full和资本指标Capital@k进行跨域归一化。我们在四个代理环境(数据库变更、客服退款以及公共tau-bench零售和航空工具使用轨迹)中实例化AAI,并报告一个实时Postgres面板,其中三个Azure托管的模型通过同一合约提出行动。边界在跨域中表现出常见的低储备拒绝和中间释放模式,仅在预算网格达到全储备需求时饱和;所需储备资本变化达22倍(Capital@50从289到6457)。该框架不强制域采用相同形状;它揭示每个域的精算几何。在实时面板中,合约在低预算下防止了所有三个模型的实现损失,但在拒绝下的承保持续性方面有所不同:模型身份是一个精算承保变量。贡献是一个用于自主代理副作用运行时精算控制的基准就绪评估框架。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑