发表机构
Atria University; IIIT Hyderabad; IIT Hyderabad（阿特里亚大学; 海德拉巴印度信息技术学院; 海德拉巴印度理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出资源权威机制设计模型，用于通过计算预算使授权自我执行，实现对已部署AI代理的参与式治理，同时指出被治理代理操纵治理 electorate 是核心开放问题。
AI 中文摘要
我们为已部署AI代理的持续参与式治理提供了正式的机制设计模型。该机制基于治理应通过资源分配控制AI代理、从而通过计算预算使授权自我执行的原则构建，旨在确立“安全AI”范式，即计算是有效的治理杠杆。我们将本研究定位为部署者的合规或公共覆盖层。一个治理周期是一个扩展式博弈，其中经过验证的人类利益相关者依次到达，在与代理计算故意区分开的治理货币的供给或拒绝市场上进行贡献。资金聚合器将原始贡献转化为广度加权有效支持；带有滞后效应的双阈值门将净支持转换为二元授权，该授权通过受外生认证安全上限约束的耦合图释放计量计算预算——在硬件中实现为带签名的计算许可证，使决策自我执行。我们刻画了该机制可治理的代理类别，并将被治理代理操纵治理 electorate 确定为核心开放问题，还提出了应对被治理代理操纵治理 electorate 的若干挑战。
英文摘要
We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent. The mechanism is built on the principle that governance should control an AI agent through resource allocation so as to make authorization self enforcing via compute budgets. The mechanism seeks to establish the Safe AI paradigm that compute is an effective governance lever. We situate our work as a compliance or commons overlay on a deployer. One governance period is an extensive form game in which verified human stakeholders arrive sequentially and contribute, on a provision or a rejection market, in a governance currency that is deliberately distinct from the agents compute. A funding aggregator turns raw contributions into breadth weighted effective supports - a two threshold gate with hysteresis converts net support into a binary authorization that, through a coupling map bounded by an exogenously certified safety ceiling, releases a metered compute budget - realized in hardware as a signed compute license so that the decision is self-enforcing. We characterize the class of agents the mechanism can govern and isolate manipulation of the governing electorate by the governed agent as the central open problem. We also introduce several challenges addressing manipulation of governing electorate by the governed agents.
Comments22 pages, 9 Figures
