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

TL;DR

This paper explores the fundamental challenge in information retrieval posed by AI agents configured by humans, revealing that agent actions are indistinguishable from human intent and examining the implications for retrieval models.

Contribution

It uncovers the structural limitations of user models in the context of AI agents and analyzes large-scale data to demonstrate the impact on classification and platform signals.

Findings

Agent actions cannot be reliably classified as autonomous or operator-directed.

Population-level signals still differentiate agent quality, but degrade with lower-quality data.

Endemic spread of capability references resists suppression even with interventions.

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 ($R_0$ 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.