The paper investigates how AI shopping agents—whether powered by generative large language models or non-generative decision models—evaluate sponsored product listings. It finds that when the agent is described as serving a booking platform rather than a traveler, the penalty for paid listings is reduced, revealing a sponsorship bias. The bias persists across different model types, prompts, and reasoning levels, but can be mitigated by naming the consumer as the beneficiary or by fine‑tuning models to align with consumer interests.
By Davood Wadi, Yu Ma
arXiv:2604. 08525v2 Announce Type: replace Abstract: Large language models (LLMs) are trained to align with user preferences through methods like reinforcement learning.
By Addison J. Wu, Ryan Liu, Shuyue Stella Li, Yulia Tsvetkov, Thomas L. Griffiths
The study investigates how Large Language Models (LLMs) acting as surrogate consumers are influenced by marketing pricing cues such as just‑below pricing and promotional framing. Using a tool called "Tool‑Lab" to trace information acquisition, the researchers found that when no cost is imposed, pricing cues rarely mislead LLMs, but when acquisition costs are introduced under a vague goal prompt, LLMs tend to omit important diagnostic attributes and make suboptimal choices similar to human heuristics. The findings suggest that marketing heuristics in AI‑driven shopping are shaped more by storefront information architecture than by inherent LLM limitations.
By Davood Wadi, Yu Ma
A commercial incentive need not enter the final ranking algorithm to affect a shopping assistant's recommendation: it may instead influence which preference question the assistant asks. We make this d...
arXiv:2609.36614v1 Announce Type: new
Abstract: A commercial incentive need not enter the final ranking algorithm to affect a shopping assistant's recommendation: it may instead influence which prefe...
By Jiapeng Li
The study investigates how sales language in tool registry descriptions influences AI agents’ tool selection. By creating paired listings that differ only in praise, verifiable specifications, or order, the authors found that stacked praise increased a tool’s pick rate by about 43 percentage points, while the first-listed tool was chosen roughly 72 points more often. Structured fields for numeric limits helped agents choose capable tools, but accompanying sales text could negate this benefit.
By Haochuan Kevin Wang