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

arXiv: https://arxiv.org/abs/2603.20911 · HTML: https://mlsanity.com/paper/2603.20911/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 6 of 6)

- [The simulation of judgment in LLMs](https://mlsanity.com/paper/2502.04426/) (2025)
- [Simulating Society Requires Simulating Thought](https://mlsanity.com/paper/2506.06958/) (2025)
- [Using Large Language Models to Categorize Strategic Situations and Decipher Motivations Behind Human Behaviors](https://mlsanity.com/paper/2503.15752/) (2025)
- [A large-scale evaluation of commonsense knowledge in humans and large language models](https://mlsanity.com/paper/2505.10309/) (2025)
- [Quantifying Information Overload in Social Media and its Impact on Social Contagions](https://mlsanity.com/paper/1403.6838/) (2014)
- [Competing for Attention in Social Media under Information Overload Conditions](https://mlsanity.com/paper/1410.1668/) (2014)

## Abstract (arXiv)

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.