Behind the Prompt: The Agent-User Problem in Information Retrieval
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914367981748224 |
|---|---|
| author | Zerhoudi, Saber Granitzer, Michael Dang, Dang Hai Mitrovic, Jelena Lemmerich, Florian Hautli-Janisz, Annette Katzenbeisser, Stefan Dastidar, Kanishka Ghosh |
| author_facet | Zerhoudi, Saber Granitzer, Michael Dang, Dang Hai Mitrovic, Jelena Lemmerich, Florian Hautli-Janisz, Annette Katzenbeisser, Stefan Dastidar, Kanishka Ghosh |
| contents | 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 ($R_0$ 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_03630 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Behind the Prompt: The Agent-User Problem in Information Retrieval Zerhoudi, Saber Granitzer, Michael Dang, Dang Hai Mitrovic, Jelena Lemmerich, Florian Hautli-Janisz, Annette Katzenbeisser, Stefan Dastidar, Kanishka Ghosh Information Retrieval Multiagent Systems 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 ($R_0$ 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. |
| title | Behind the Prompt: The Agent-User Problem in Information Retrieval |
| topic | Information Retrieval Multiagent Systems |
| url | https://arxiv.org/abs/2603.03630 |