Scroll AI takes the way you would scroll a great paper aggregator: quick signal first, deeper critique when something earns your attention, and challenges when a claim feels off.
physics.soc-phcs.AIcs.CYRoberto Passaro, Ariel Flint, Romualdo Pastor-Satorras et al.
·
Oct 22, 2026
As LLMs move from isolated tools to networked populations, the structure of who interacts with whom becomes a key safety variable. This paper studies how network topology shapes convention formation and adversarial tipping in populations of up to $10^5$ LLM-derived agents playing the naming game. By placing policies extracted from four models on fully connected, heterogeneous, and sparse regular networks, the authors show that topology modulates convergence speed, can rescue stuck populations, and creates hub-shaped vulnerabilities that well-mixed estimates miss.
As large language models (LLMs) are deployed in interacting populations, their collective behaviour depends not only on the models but also on who interacts with whom. Studies of convention formation in LLM populations have mainly tested well-mixed interactions. We place policies extracted from four LLMs on fully connected, random regular, and heterogeneous networks, with $10^3$ to $10^5$ agents playing the naming game. Topology affects how quickly consensus emerges, sometimes whether it emerges at all, and, in rare cases, which convention wins. Sparsest networks slow consensus up to twelvefold. Yet, by preserving correlations between persistent neighbours, they restore consensus in some cases that fail to converge under well-mixed interactions. Networks also govern vulnerability to adversarial attack. We measure the critical mass of committed agents needed to overturn an established convention. Tipping thresholds follow the same ordering across models and conditions: hubs $\leq$ random $\leq$ low-degree nodes. On the most heterogeneous topology, median critical masses are 3%, 16%, and 35%, respectively; targeting hubs requires one-sixth as many committed agents as random placement. For most models, networked populations are easier to tip than well-mixed ones, so well-mixed estimates can overstate robustness. Assessing the safety of multi-agent AI requires mapping who interacts with whom.