Do LLM-Driven Agents Exhibit Engagement Mechanisms? Controlled Tests of Information Load, Descriptive Norms, and Popularity Cues

TL;DR

This study investigates how large language model-driven agents respond to social media engagement cues, revealing systematic behavioral changes under different information loads and norms, with implications for simulation research methodology.

Contribution

It demonstrates that LLM-driven agents exhibit context-dependent engagement behaviors influenced by manipulated social cues, advancing understanding of their use in social simulations.

Findings

Engagement varies systematically with information load and norms.

Sensitivity to popularity cues depends on context.

Behavioral responses reflect conditional rather than fixed prompt compliance.

Abstract

Large language models make agent-based simulation more behaviorally expressive, but they also sharpen a basic methodological tension: fluent, human-like output is not, by itself, evidence for theory. We evaluate what an LLM-driven simulation can credibly support using information engagement on social media as a test case. In a Weibo-like environment, we manipulate information load and descriptive norms, while allowing popularity cues (cumulative likes and Sina Weibo-style cumulative reshares) to evolve endogenously. We then ask whether simulated behavior changes in theoretically interpretable ways under these controlled variations, rather than merely producing plausible-looking traces. Engagement responds systematically to information load and descriptive norms, and sensitivity to popularity cues varies across contexts, indicating conditionality rather than rigid prompt compliance. We discuss methodological implications for simulation-based communication research, including multi-condition stress tests, explicit no-norm baselines because default prompts are not blank controls, and design choices that preserve endogenous feedback loops when studying bandwagon dynamics.