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

Computer Science > Artificial Intelligence [Submitted on 21 Mar 2026] Do LLM-Driven Agents Exhibit Engagement Mechanisms? Controlled Tests of Information Load, Descriptive Norms, and Popularity Cues Tai-Quan Peng, Yuan Tian, Songsong Liang, Dazhen Deng, Yingcai Wu 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. Subjects: Artificial Intelligence (cs.AI); Computers and Society (cs.CY) Cite as: arXiv:2603.20911 [cs.AI]   (or arXiv:2603.20911v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.20911 Focus to learn more Submission history From: Tai-Quan Peng [view email] [v1] Sat, 21 Mar 2026 18:50:22 UTC (2,424 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.CY References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)