Preprint
When Agents Shop for You: Role Coherence in AI-Mediated Markets
ArXiv.org
Cornell University
04/29/2026
DOI: 10.48550/arxiv.2604.26220
Abstract
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.
Details
- Title: Subtitle
- When Agents Shop for You: Role Coherence in AI-Mediated Markets
- Creators
- Soogand AlaviSalar Nozari
- Resource Type
- Preprint
- Publication Details
- ArXiv.org
- DOI
- 10.48550/arxiv.2604.26220
- ISSN
- 2331-8422
- Publisher
- Cornell University; Ithaca, New York
- Language
- English
- Date posted
- 04/29/2026
- Academic Unit
- Marketing
- Record Identifier
- 9985157518002771
Metrics
1 Record Views