SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

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 att

Read original source ↗ Open in workspace

recordType

paper

region

Global