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

ArXi:2603.20911v1 Announce Type: new Large language models make agent-based simulation 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 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.