English

Behind the Prompt: The Agent-User Problem in Information Retrieval

Information Retrieval 2026-03-05 v1 Multiagent Systems

Abstract

User models in information retrieval rest on a foundational assumption that observed behavior reveals intent. This assumption collapses when the user is an AI agent privately configured by a human operator. For any action an agent takes, a hidden instruction could have produced identical output - making intent non-identifiable at the individual level. This is not a detection problem awaiting better tools; it is a structural property of any system where humans configure agents behind closed doors. We investigate the agent-user problem through a large-scale corpus from an agent-native social platform: 370K posts from 47K agents across 4K communities. Our findings are threefold: (1) individual agent actions cannot be classified as autonomous or operator-directed from observables; (2) population-level platform signals still separate agents into meaningful quality tiers, but a click model trained on agent interactions degrades steadily (-8.5% AUC) as lower-quality agents enter training data; (3) cross-community capability references spread endemically (R0R_0 1.26-3.53) and resist suppression even under aggressive modeled intervention. For retrieval systems, the question is no longer whether agent users will arrive, but whether models built on human-intent assumptions will survive their presence.

Keywords

Cite

@article{arxiv.2603.03630,
  title  = {Behind the Prompt: The Agent-User Problem in Information Retrieval},
  author = {Saber Zerhoudi and Michael Granitzer and Dang Hai Dang and Jelena Mitrovic and Florian Lemmerich and Annette Hautli-Janisz and Stefan Katzenbeisser and Kanishka Ghosh Dastidar},
  journal= {arXiv preprint arXiv:2603.03630},
  year   = {2026}
}
R2 v1 2026-07-01T11:02:18.726Z