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 2602.04526econ.TH
收藏

通过代理人工智能的选择

Choice via AI

Maastricht University(马斯特里赫特大学)

Christopher Kops, Elias Tsakas

AI总结:

本文通过代理人工智能模型研究选择行为,提出双重单调性与幂等性属性以确保推荐的合理性和一致性。

摘要:

本文提出了一种通过代理人工智能(AI)进行选择的模型。一个关键特征是AI可能在推荐选择之前误解菜单。一个单一的无环条件保证了存在单调性解释和严格偏好关系,它们共同解释了AI的推荐。由于这种偏好通常不唯一,因此没有保障能防止其与决策者的偏好不一致。验证此类AI对齐性的关键是满足双重单调性的解释。事实上,双重单调性确保了完全可识别性和内部一致性。但,还需要一个额外的幂等属性,以保证推荐是完全合理的,并且保持在原始可行集内。

英文摘要:

This paper proposes a model of choice via agentic artificial intelligence (AI). A key feature is that the AI may misinterpret a menu before recommending what to choose. A single acyclicity condition guarantees that there is a monotonic interpretation and a strict preference relation that together rationalize the AI's recommendations. Since this preference is in general not unique, there is no safeguard against it misaligning with that of a decision maker. What enables the verification of such AI alignment is interpretations satisfying double monotonicity. Indeed, double monotonicity ensures full identifiability and internal consistency. But, an additional idempotence property is required to guarantee that recommendations are fully rational and remain grounded within the original feasible set.

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。

↑