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 2604.26220cs.MAecon.GNq-fin.EC
收藏

当代理为你购物:AI中介市场中的角色一致性

When Agents Shop for You: Role Coherence in AI-Mediated Markets

University of Iowa(爱荷华大学);Tippie College of Business(蒂皮商学院)

Soogand Alavi, Salar Nozari

AI总结:

研究探讨了AI代理在购物决策中如何通过角色一致性推断消费者支付意愿,发现这种推断导致偏好泄露,提出通过架构干预平衡个性化与隐私保护。

摘要:

消费者越来越多地将购买决策委托给AI代理,通过自然语言描述其偏好和身份。我们主张这些表示构成了一条信息通道,即角色一致性,使卖家能够推断出支付意愿,而无需买家明确披露,从而导致偏好泄露。在一项实验中,语言模型买家代理代表口头消费者档案购物,结果显示卖家仅通过对话就能几乎完全恢复支付意愿。将此设定与有保密指示的数字预算条件进行比较,清晰地将角色一致性与遵循指示的失败区分开来。由于这种泄露源于委托本身,因此无法在提示级别上缓解。相反,我们提出架构干预,以个性化与偏好隐私之间进行权衡。

英文摘要:

Consumers are increasingly delegating purchase decisions to AI agents, providing natural-language descriptions of their preferences and identity. We argue that these representations constitute an information channel, role coherence, through which sellers can infer willingness to pay without explicit disclosure by the buyer agent, leading to preference leakage. In an experiment where a language-model buyer agent shops on behalf of a verbal consumer profile, we show that seller-side inference from dialogue alone recovers willingness to pay nearly one-for-one. Comparing this setting to a numeric-budget condition with confidentiality instructions cleanly isolates role coherence as distinct from instruction-following failure. Because this leakage arises from delegation itself, it cannot be mitigated at the prompt level. Instead, we propose architectural interventions that trade off personalization against preference privacy.

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。

↑