发表机构
Desautels Faculty of Management; McGill University（德索泰尔管理学院; 麦吉尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过Tool-Lab方法考察定价线索对AI购物代理的影响，发现模糊目标与信息获取成本促使LLM省略关键属性并采用人类启发式策略，表明营销影响受信息架构而非模型固有缺陷驱动。
AI 中文摘要
消费者越来越多地将购买决策委托给作为替代消费者的大型语言模型（LLMs）。通过使用“Tool-Lab”——一种信息板过程追踪的改编方法，将产品属性置于昂贵的工具调用之后——我们研究了营销定价线索（即略低于整数定价和促销框架）如何影响AI购物代理。我们追踪了来自三家供应商的八个商业部署LLM在选择前的信息获取过程。在零成本条件下，定价线索很少误导。在模糊目标提示下施加获取成本，导致LLM省略计算单价所需的诊断属性，并选择类似于人类启发式策略的次优选择。相对于主要保留诊断性搜索和选择最优性的具体目标提示，约束条件下的模糊目标提示创造了一种搜索介导的脆弱性。这项研究表明，委托AI购物中的营销启发式策略受店面信息架构支配，而不一定是不可变的LLM缺陷。
英文摘要
Consumers increasingly delegate purchasing decisions to Large Language Models (LLMs) acting as surrogate consumers. Using "Tool-Lab," an adaptation of information-board process tracing that places product attributes behind costly tool calls, we examine how marketing pricing cues (i.e., just-below pricing and promotional framing) influence AI shopping agents. Across eight commercially deployed LLMs from three providers, we trace pre-choice information acquisition. Under zero cost, pricing cues rarely mislead. Imposing acquisition costs under a vague goal prompt leads LLMs to omit diagnostic attributes required to compute unit price and choose suboptimal choices resembling human heuristics. Relative to a specific goal prompt that mainly preserves diagnostic search and choice optimality, a vague goal prompt under constraints creates a search-mediated vulnerability. This research demonstrates that marketing heuristics in delegated AI shopping are governed by storefront information architecture, not necessarily immutable LLM flaws.
