arXiv (Cornell University) · 2026 · Preprint

IO Factory: Simulating AI-Enabled Influence Campaigns at Scale

Łukasz Olejnik et al., with Jonas R. Kunst

In brief

A new framework, IO Factory, that simulates AI-enabled influence campaigns end to end—from planning and platform action to exposure, interpretation, and adaptation—inside a controlled synthetic platform. Tested across configurations of up to 100,000 agents, it executes campaign timelines at scale and produces inspectable records of exposure and measured shifts in configured belief variables, supporting reproducible research and red-team analysis of coordinated manipulation.

Figure from the article: “IO Factory: Simulating AI-Enabled Influence Campaigns at Scale”
Figure from the article · arXiv (Cornell University), 2026

Abstract

We introduce IO Factory, an AI-driven framework for simulating information and influence campaigns as fully integrated, traceable processes. The threat of digital manipulation now extends beyond persuasive text from individual language models to AI swarms, i.e., persistent groups of coordinated agents that adapt to platform feedback and disguise organized campaigns as ordinary social interaction. Because such campaigns cannot be identified from isolated messages alone, they must be analyzed across a continuous spectrum of planning, platform action, exposure, interpretation, measurement, and adaptation. IO Factory represents this process inside a controlled simulated platform, linking actor roles, platform actions, exposure records, structured model-based evaluations, and configured changes in the simulated population. We implement the architecture and evaluate it across configurations of up to 100,000 agents. The results show that IO Factory executes campaign timelines at scale and produces inspectable evidence of exposure and measured movement in configured belief variables. By recording the actors, objectives, action constraints, exposure paths, and measurement rules used in each run, IO Factory supports reproducible research and red-team analysis of coordinated influence.

Read the full article ↗ DOI: 10.48550/arxiv.2608.10920