IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2608.22697.html

Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf

Author

Listed:
  • Davood Wadi
  • Yu Ma

Abstract

When shopping is delegated to AI agents, it is unclear whether the ranking advantage documented for humans persists. Across 7,000 sessions with five large language models (LLMs) and varying reasoning effort, we compare AI agents with human field data. AI agents search more extensively than human consumers. As with humans, lower-ranked listings are less likely to be inspected, although the effect is smaller for AI agents. Unlike humans, AI agents show a pattern consistent with the lost-in-the-middle effect, whereby middle listings have the lowest probability of inspection. At the choice stage, position effects are concentrated at lower reasoning effort, but higher effort reduces the middle penalty for every LLM that exhibits it. These findings suggest that, when search is delegated, displayed attributes may matter more than placement, and that exposure to position bias depends on how the AI agent is configured.

Suggested Citation

  • Davood Wadi & Yu Ma, 2026. "Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf," Papers 2608.22697, arXiv.org, revised Oct 2026.
    • Handle: RePEc:arx:papers:2608.22697
    as

    Download full text from publisher

    File URL: https://arxiv.org/pdf/2608.22697
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Hauser, John R., 2014. "Consideration-set heuristics," Journal of Business Research, Elsevier, vol. 67(8), pages 1688-1699.
    2. Raluca M. Ursu, 2018. "The Power of Rankings: Quantifying the Effect of Rankings on Online Consumer Search and Purchase Decisions," Marketing Science, INFORMS, vol. 37(4), pages 530-552, August.
    3. Honka, Elisabeth & Seiler, Stephan & Ursu, Raluca, 2024. "Consumer search: What can we learn from pre-purchase data?," Journal of Retailing, Elsevier, vol. 100(1), pages 114-129.
    4. Ali Goli & Amandeep Singh, 2024. "Frontiers: Can Large Language Models Capture Human Preferences?," Marketing Science, INFORMS, vol. 43(4), pages 709-722, July.
    5. Sridhar Narayanan & Kirthi Kalyanam, 2015. "Position Effects in Search Advertising and their Moderators: A Regression Discontinuity Approach," Marketing Science, INFORMS, vol. 34(3), pages 388-407, May.
    6. Honka, Elisabeth & Seiler, Stephan & Ursu, Raluca, 2024. "Consumer Search: What Can We Learn from Pre-Purchase Data?," CEPR Discussion Papers 18848, Centre for Economic Policy Research.
    7. Raluca Ursu & Stephan Seiler & Elisabeth Honka, 2025. "The sequential search model: A framework for empirical research," Quantitative Marketing and Economics (QME), Springer, vol. 23(1), pages 165-213, March.
    8. Punj, Girish & Moore, Robert, 2009. "Information search and consideration set formation in a web-based store environment," Journal of Business Research, Elsevier, vol. 62(6), pages 644-650, June.
    9. Rafael P. Greminger, 2022. "Trade-Offs Between Ranking Objectives: Descriptive Evidence and Structural Estimation," Papers 2210.16408, arXiv.org, revised Mar 2026.
    10. Raluca M. Ursu & Qianyun Zhang & Elisabeth Honka, 2023. "Search Gaps and Consumer Fatigue," Marketing Science, INFORMS, vol. 42(1), pages 110-136, January.
    11. Yi-Chun Akchen & Dmitry Mitrofanov, 2023. "Consider or Choose? The Role and Power of Consideration Sets," Papers 2302.04354, arXiv.org, revised Feb 2025.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Louis-Daniel Pape & Michelangelo Rossi, 2026. "Is Competition Only One Click Away? The Digital Markets Act’s Impact on Google Maps," Marketing Science, INFORMS, vol. 45(3), pages 596-613, May.
    2. Yuyang Tan & Hao Gong & Chunxiang Guo, 2025. "Bi-Objective Optimization of Product Selection and Ranking Considering Sequential Search," SAGE Open, , vol. 15(3), pages 21582440251, August.
    3. Yuyan Wang & Long Tao & Xian Xing Zhang, 2025. "Recommending for a Multi-Sided Marketplace: A Multi-Objective Hierarchical Approach," Marketing Science, INFORMS, vol. 44(1), pages 1-29, January.
    4. Krefeld-Schwalb, Antonia & Martinovici, Ana & Orquin, Jacob L. & Aribarg, Anocha & Erdem, Tulin & Johnson, Eric J. & Reeck, Crystal & Schley, Dan R. & Smith, Stephanie M. & Speekenbrink, Maarten & Ste, 2026. "Search in service of choice: An agenda for comparing, extending, and integrating consumer search models," International Journal of Research in Marketing, Elsevier, vol. 43(2), pages 485-499.
    5. Raluca Ursu & Stephan Seiler & Elisabeth Honka, 2025. "The sequential search model: A framework for empirical research," Quantitative Marketing and Economics (QME), Springer, vol. 23(1), pages 165-213, March.
    6. Ali Aouad & Danny Segev, 2021. "Display Optimization for Vertically Differentiated Locations Under Multinomial Logit Preferences," Management Science, INFORMS, vol. 67(6), pages 3519-3550, June.
    7. Tinghan Zhang, 2025. "A Ranking Representation of Optimal Sequential Search," Papers 2501.07514, arXiv.org, revised May 2026.
    8. Pedro M. Gardete & Megan Hunter, 2024. "Multiattribute Search: Empirical Evidence and Information Design," Marketing Science, INFORMS, vol. 43(5), pages 1052-1080, September.
    9. Robert Donnelly & Ayush Kanodia & Ilya Morozov, 2024. "Welfare Effects of Personalized Rankings," Marketing Science, INFORMS, vol. 43(1), pages 92-113, January.
    10. Honka, Elisabeth & Seiler, Stephan & Ursu, Raluca, 2024. "Consumer search: What can we learn from pre-purchase data?," Journal of Retailing, Elsevier, vol. 100(1), pages 114-129.
    11. Ivy Chu Dang & Raluca M. Ursu & Pradeep K. Chintagunta, 2026. "Going back to move forward? How search revisits on a website we built inform us about search outcomes," Quantitative Marketing and Economics (QME), Springer, vol. 24(1), pages 1-39, December.
    12. Ho Huy Tuu & Nguyen Huu Khoi & Svein Ottar Olsen, 2021. "How consumer innovativeness, technological expertise, and consideration set size can explain mobile commerce use: An extended understanding using a moderation–mediation model," Information Systems and e-Business Management, Springer, vol. 19(3), pages 1015-1038, September.
    13. Raluca Mihaela Ursu & Andrey Simonov & Eunkyung An, 2025. "Online Advertising as Passive Search," Management Science, INFORMS, vol. 71(2), pages 1050-1073, February.
    14. Loock, Moritz & Hinnen, Gieri, 2015. "Heuristics in organizations: A review and a research agenda," Journal of Business Research, Elsevier, vol. 68(9), pages 2027-2036.
    15. Xiang Hui & Meng Liu & Raphael Thomadsen, 2022. "Quality Certificates Alleviate Consumer Aversion to Sponsored Search Advertising," CESifo Working Paper Series 9886, CESifo.
    16. Ata Jameei Osgouei & Andrew T. Ching & Brian T. Ratchford & Shervin Shahrokhi Tehrani, 2026. "Estimating Position and Social Influence Effects in Online Search," Marketing Science, INFORMS, vol. 45(1), pages 203-223, January.
    17. Harris, Mark N. & Novarese, Marco & Wilson, Chris M., 2022. "Being in the right place: A natural field experiment on the causes of position effects in individual choice," Journal of Economic Behavior & Organization, Elsevier, vol. 194(C), pages 24-40.
    18. Mohammad Amin Farzaneh & Sajad Modaresi & Ashwin Venkataraman, 2026. "A Feature-Based Consideration Set Choice Model for Online Retailing," Manufacturing & Service Operations Management, INFORMS, vol. 28(3), pages 706-725, May.
    19. Leon Yang Chu & Hamid Nazerzadeh & Heng Zhang, 2020. "Position Ranking and Auctions for Online Marketplaces," Management Science, INFORMS, vol. 66(8), pages 3617-3634, August.
    20. Aishwarya Deep Shukla & Guodong (Gordon) Gao & Ritu Agarwal, 2021. "How Digital Word-of-Mouth Affects Consumer Decision Making: Evidence from Doctor Appointment Booking," Management Science, INFORMS, vol. 67(3), pages 1546-1568, March.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2608.22697. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: https://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.