Shopping by algorithm: How agentic AI deploys human heuristics as a surrogate consumer

2026-09-23

AI Summary

研究通过Tool-Lab方法探讨了营销定价线索如何影响作为消费者代理的大型语言模型（LLMs）的信息获取和决策过程，揭示了在模糊目标提示下LLMs易受误导的现象。

Abstract

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.

Problem

• Large Language Models
• marketing pricing cues
• heuristics
• information acquisition cost
• choice behavior

Innovation

• Large Language Models
• marketing heuristics
• information acquisition cost
• surrogate consumers
• search-mediated vulnerability